{"data":[{"project":"default","id":"enso.gpqa_diamond-heldout-1.6.6-best-single","benchmark":"enso.gpqa_diamond","split":"heldout","system":"best-single","version":"","baseline":true,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:79c691a3d9e07d4963a8a01964209c6cd1a80a3f763175fcc641b5e9eddd9924","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":159,"answered":159,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"a27372087553d1d73d93c58aa67b77724928531e05e3e4e1ba1c2992d7250821","measures":[{"category":"all","metric":"accuracy","value":0.930818,"lo":null,"hi":null,"n":148,"of":159},{"category":"all","metric":"stderr","value":0.0201,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":159,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":148,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":5.1556,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-heldout-1.6.6-enso","benchmark":"enso.gpqa_diamond","split":"heldout","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:79c691a3d9e07d4963a8a01964209c6cd1a80a3f763175fcc641b5e9eddd9924","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":159,"answered":159,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"91d4ed4fa94ffdbb823fd446cef9fe244866c1222ca744d27a39236338d45aa6","measures":[{"category":"all","metric":"accuracy","value":0.937107,"lo":null,"hi":null,"n":149,"of":159},{"category":"all","metric":"stderr","value":0.0193,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":159,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":149,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":10.0316,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-heldout-1.6.6-enso-flash","benchmark":"enso.gpqa_diamond","split":"heldout","system":"enso-flash","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:79c691a3d9e07d4963a8a01964209c6cd1a80a3f763175fcc641b5e9eddd9924","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":159,"answered":159,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"d01e368c373b880dfd2d3bf6a0d983b04d27df489051c2e4feba83142b40d717","measures":[{"category":"all","metric":"accuracy","value":0.90566,"lo":null,"hi":null,"n":144,"of":159},{"category":"all","metric":"stderr","value":0.0232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":159,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":144,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":3.2602,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-heldout-1.6.6-enso-ultra","benchmark":"enso.gpqa_diamond","split":"heldout","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:79c691a3d9e07d4963a8a01964209c6cd1a80a3f763175fcc641b5e9eddd9924","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":159,"answered":159,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"c7656c111abccca52849ad1c91fd2e70dea4297447953a8bb39c9f532836a17e","measures":[{"category":"all","metric":"accuracy","value":0.955975,"lo":null,"hi":null,"n":152,"of":159},{"category":"all","metric":"stderr","value":0.0163,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":159,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":152,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":14.7631,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-lockbox-1.6.6-enso","benchmark":"enso.gpqa_diamond","split":"lockbox","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:8a10bf6a2c655ae556e8d8bd8d6f8969a0e1c263684a7b4f8c4272ad2e38c256","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":39,"answered":39,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"feab35e077a8666594fc96db800699fd8ef54e526e689e9e907dc09f7029a5af","measures":[{"category":"all","metric":"accuracy","value":0.923077,"lo":null,"hi":null,"n":36,"of":39},{"category":"all","metric":"stderr","value":0.0427,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":39,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":36,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":9.2669,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-lockbox-1.6.6-enso-flash","benchmark":"enso.gpqa_diamond","split":"lockbox","system":"enso-flash","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:8a10bf6a2c655ae556e8d8bd8d6f8969a0e1c263684a7b4f8c4272ad2e38c256","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":39,"answered":39,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"6933ccfcebfa3b800186b98928176e60add2c5a3fa3d894f4e4d6aa625d7bea4","measures":[{"category":"all","metric":"accuracy","value":0.948718,"lo":null,"hi":null,"n":37,"of":39},{"category":"all","metric":"stderr","value":0.0353,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":39,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":37,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":2.5885,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-lockbox-1.6.6-enso-ultra","benchmark":"enso.gpqa_diamond","split":"lockbox","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:8a10bf6a2c655ae556e8d8bd8d6f8969a0e1c263684a7b4f8c4272ad2e38c256","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":39,"answered":39,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"861a8bd01e2495ca11abb1c5d71b3dc1b38dffe4b64f9fdadd7933b5fd789116","measures":[{"category":"all","metric":"accuracy","value":0.948718,"lo":null,"hi":null,"n":37,"of":39},{"category":"all","metric":"stderr","value":0.0353,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":39,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":37,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"usd_per_1k","value":10.5556,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"corrected","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-20260720-212511-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-20T23:56:21Z","by":"enso-bench","completion":"complete","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"stderr","value":0.0182,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":184,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":360.6823935,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-corpus-train-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":89,"when":"","ended":"2026-07-21T19:37:53Z","by":"enso-bench","completion":"partial","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.414141,"lo":null,"hi":null,"n":82,"of":198},{"category":"answered","metric":"accuracy","value":0.921348,"lo":null,"hi":null,"n":82,"of":89},{"category":"all","metric":"stderr","value":0.035,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":82,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":109,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":109,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":167.748427,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-fill-fable-5.1","benchmark":"enso.gpqa_diamond","split":"test","system":"fable-5.1","version":"anthropic/claude-fable-5.1","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":193,"when":"","ended":"2026-10-16T19:53:15Z","by":"enso-bench","completion":"partial","key":"7f58e7c906da63cba2740743d70c7da73e3b82ceefe8f93b2a4fcefbd3e721b9","measures":[{"category":"all","metric":"accuracy","value":0.878788,"lo":null,"hi":null,"n":174,"of":198},{"category":"answered","metric":"accuracy","value":0.901554,"lo":null,"hi":null,"n":174,"of":193},{"category":"all","metric":"stderr","value":0.0232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":174,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":5,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":5,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":75407,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":149482,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":193,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":9.1582,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-fill-haiku-5.5","benchmark":"enso.gpqa_diamond","split":"test","system":"haiku-5.5","version":"anthropic/claude-haiku-5.5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-10-16T18:51:14Z","by":"enso-bench","completion":"complete","key":"de41195b7ab68ba8795ce48f4ece6ca96b6af2813be79e9358814cdd305e4b7b","measures":[{"category":"all","metric":"accuracy","value":0.833333,"lo":null,"hi":null,"n":165,"of":198},{"category":"all","metric":"stderr","value":0.0265,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":165,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78517,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":364129,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":0.2114,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-fill-opus-5.5","benchmark":"enso.gpqa_diamond","split":"test","system":"opus-5.5","version":"anthropic/claude-opus-5.5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":195,"when":"","ended":"2026-10-16T19:25:41Z","by":"enso-bench","completion":"partial","key":"a31b9b740fbbe5f5945893a6e618e766c3ad79146655e7e5c9d2d4b5c3773c79","measures":[{"category":"all","metric":"accuracy","value":0.909091,"lo":null,"hi":null,"n":180,"of":198},{"category":"answered","metric":"accuracy","value":0.923077,"lo":null,"hi":null,"n":180,"of":195},{"category":"all","metric":"stderr","value":0.0204,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":180,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":3,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":3,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":76538,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":173489,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":195,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":4.2027,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-fill-sonnet-5.5","benchmark":"enso.gpqa_diamond","split":"test","system":"sonnet-5.5","version":"anthropic/claude-sonnet-5.5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":197,"when":"","ended":"2026-10-16T19:25:13Z","by":"enso-bench","completion":"partial","key":"68f5d376943bfea01e7dd54a37856b2eaef2c75bd7cad5d062497e522c5293c2","measures":[{"category":"all","metric":"accuracy","value":0.90404,"lo":null,"hi":null,"n":179,"of":198},{"category":"answered","metric":"accuracy","value":0.908629,"lo":null,"hi":null,"n":179,"of":197},{"category":"all","metric":"stderr","value":0.0209,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":179,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":1,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":1,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":77500,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":169690,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":197,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":2.0612,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-claude-5-sonnet","benchmark":"enso.gpqa_diamond","split":"test","system":"claude-5-sonnet","version":"anthropic-claude-5-sonnet","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T10:29:15Z","by":"enso-bench","completion":"complete","key":"e213f9edd141f55d472b97049490e6ad4d8c91f8eca8aa897d585b06b60eb11e","measures":[{"category":"all","metric":"accuracy","value":0.777778,"lo":null,"hi":null,"n":154,"of":198},{"category":"all","metric":"stderr","value":0.0295,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":154,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78121,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":550804,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":8.4964,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-deepseek-v4-pro","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-v4-pro","version":"deepseek-v4-pro","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T09:02:00Z","by":"enso-bench","completion":"complete","key":"c4d9db760b1830876509320341493a706443343cd02fea28917a56adaeb3586d","measures":[{"category":"all","metric":"accuracy","value":0.742424,"lo":null,"hi":null,"n":147,"of":198},{"category":"all","metric":"stderr","value":0.0311,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":147,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":52523,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":109126,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":0.2089,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-enso","benchmark":"enso.gpqa_diamond","split":"test","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T07:41:21Z","by":"enso-bench","completion":"complete","key":"9c1583fca7210237c1c8d3ca222e85d90b7c95072f50fa5d9445bccdf085679a","measures":[{"category":"all","metric":"accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"stderr","value":0.0182,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":184,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":5.5787985,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-enso-flash","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-flash","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T07:18:27Z","by":"enso-bench","completion":"complete","key":"bb9043fe09075e92903bb723d2838ca017836eca4b9899b5884df743e1df8d4f","measures":[{"category":"all","metric":"accuracy","value":0.722222,"lo":null,"hi":null,"n":143,"of":198},{"category":"all","metric":"stderr","value":0.0318,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":143,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":0.22131779999999998,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T08:48:43Z","by":"enso-bench","completion":"complete","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"stderr","value":0.0182,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":184,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":20.2021435,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-fable-5","benchmark":"enso.gpqa_diamond","split":"test","system":"fable-5","version":"anthropic-claude-fable-5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T09:51:13Z","by":"enso-bench","completion":"complete","key":"e55d68c398dba7f168589009bd82f191ed394704dfe71154dd2656a8b635b575","measures":[{"category":"all","metric":"accuracy","value":0.828283,"lo":null,"hi":null,"n":164,"of":198},{"category":"all","metric":"stderr","value":0.0268,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":164,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78121,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":181711,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":2.96,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-gpt-4o","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-4o","version":"openai-gpt-4o","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T09:59:04Z","by":"enso-bench","completion":"complete","key":"04fc71bdf17ec36b33f77409e7f96a93bbfe4b102966d64036ee96f7cdb23f20","measures":[{"category":"all","metric":"accuracy","value":0.545455,"lo":null,"hi":null,"n":108,"of":198},{"category":"all","metric":"stderr","value":0.0354,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":108,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":55114,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":144289,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":1.5807,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-gpt-5.5","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.5","version":"openai-gpt-5.5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T09:36:27Z","by":"enso-bench","completion":"complete","key":"ab5c826e5f694c6e23c7a8635e89356886128f3866e4b76e992002a7a1133a3a","measures":[{"category":"all","metric":"accuracy","value":0.89899,"lo":null,"hi":null,"n":178,"of":198},{"category":"all","metric":"stderr","value":0.0214,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":178,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":54916,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":389125,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":352545,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":3.9599,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-gpt-5.6-sol","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.6-sol","version":"openai-gpt-5.6-sol","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T06:52:53Z","by":"enso-bench","completion":"complete","key":"794b3072020151f26a34fd2aca22bb310f2dba05b296666a305e0ab53f605ab4","measures":[{"category":"all","metric":"accuracy","value":0.919192,"lo":null,"hi":null,"n":182,"of":198},{"category":"all","metric":"stderr","value":0.0194,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":182,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":54916,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":192804,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":155827,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":1.9967,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-frontier-opus-4.8","benchmark":"enso.gpqa_diamond","split":"test","system":"opus-4.8","version":"anthropic-claude-opus-4.8","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T07:03:15Z","by":"enso-bench","completion":"complete","key":"d48d792fbad9cc374d6cccc1256df7e0c41ef6652cceb35d281e9001c79ba48b","measures":[{"category":"all","metric":"accuracy","value":0.863636,"lo":null,"hi":null,"n":171,"of":198},{"category":"all","metric":"stderr","value":0.0244,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":171,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78121,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":130593,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":10.9663,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-k3fix-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":68,"when":"","ended":"2026-07-20T11:27:28Z","by":"enso-bench","completion":"partial","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.328283,"lo":null,"hi":null,"n":65,"of":198},{"category":"answered","metric":"accuracy","value":0.955882,"lo":null,"hi":null,"n":65,"of":68},{"category":"all","metric":"stderr","value":0.0334,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":65,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":130,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":130,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":34.128028,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-max-deepseek-v4-pro","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-v4-pro","version":"deepseek-v4-pro","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-20T02:54:52Z","by":"enso-bench","completion":"complete","key":"c4d9db760b1830876509320341493a706443343cd02fea28917a56adaeb3586d","measures":[{"category":"all","metric":"accuracy","value":0.752525,"lo":null,"hi":null,"n":149,"of":198},{"category":"all","metric":"stderr","value":0.0307,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":149,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":113354,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":0.2204,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-max-fable-5","benchmark":"enso.gpqa_diamond","split":"test","system":"fable-5","version":"claude-fable-5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":170,"when":"","ended":"2026-07-20T00:24:36Z","by":"enso-bench","completion":"partial","key":"a04f6e8f21c114b32c21956cfceca66f0c32c338335a8a59da2595e06deb7b3b","measures":[{"category":"all","metric":"accuracy","value":0.80303,"lo":null,"hi":null,"n":159,"of":198},{"category":"answered","metric":"accuracy","value":0.935294,"lo":null,"hi":null,"n":159,"of":170},{"category":"all","metric":"stderr","value":0.0283,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":159,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":28,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":66379,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":1.1778,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-max-gpt-5.6-sol","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.6-sol","version":"gpt-5.6-sol","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":193,"when":"","ended":"2026-07-19T23:54:55Z","by":"enso-bench","completion":"partial","key":"fd799e94ad3e216e5f77621094625282051d543fffa91003752ff22f5e1b93e6","measures":[{"category":"all","metric":"accuracy","value":0.924242,"lo":null,"hi":null,"n":183,"of":198},{"category":"answered","metric":"accuracy","value":0.948187,"lo":null,"hi":null,"n":183,"of":193},{"category":"all","metric":"stderr","value":0.0188,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":183,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":5,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":34023,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-max-opus-4.8","benchmark":"enso.gpqa_diamond","split":"test","system":"opus-4.8","version":"claude-opus-4.8","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":196,"when":"","ended":"2026-07-20T00:07:57Z","by":"enso-bench","completion":"partial","key":"4580c668765fd1573cb6c76f6ae9f522991c86ca06d951976ffeeff178c3202f","measures":[{"category":"all","metric":"accuracy","value":0.873737,"lo":null,"hi":null,"n":173,"of":198},{"category":"answered","metric":"accuracy","value":0.882653,"lo":null,"hi":null,"n":173,"of":196},{"category":"all","metric":"stderr","value":0.0236,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":173,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":2,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":106682,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":8.9116,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K1","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K1","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"538301c6b400c7751ff468486387063ed504e831b95b11c38823ec7bcf28f3a2","measures":[{"category":"all","metric":"oracle_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9293,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9293,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9293,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":1,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K10","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K10","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"8b1ce4afa076d70299c84b1afc97ca16c21ada1471f52a9bfa290e9d07b22931","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9192,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9178,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":10,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K11","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K11","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"91dffa30ba522c23b4f1b4c6dd2069347ea428b1422d3ad8dec0226bb537fdc2","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9165,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9155,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":11,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K12","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K12","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"e643ca1592500865ae371d220ec5f2211345522a27bd02e35bfe13dd066d773b","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9125,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9158,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":12,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K13","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K13","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"026314c653c29bbcb75f62a90442f30cc6cbea121ccb982f0486cf7c12ff6386","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.8997,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9118,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":13,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K14","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K14","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"7db5654e790872e5ba1c138b8fa7eb7daa288fc11cc20088e11b383f0974ff45","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.8949,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9104,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":14,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K15","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K15","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"a32ae7afad480b0f30ff5d224aca9c9e816f9f0057311546535037368118bf3e","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.8939,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9101,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K2","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K2","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"55ccd4b42c0cf1fa415c68a5d525b4aa99df59e26391596a1a5d3fc46edf4ee9","measures":[{"category":"all","metric":"oracle_accuracy","value":0.974747,"lo":null,"hi":null,"n":193,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9384,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9279,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9172,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":2,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K3","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K3","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"974fd1962bff8c1856df51957068ebd839326b092d868ae8b624991d6078a2a2","measures":[{"category":"all","metric":"oracle_accuracy","value":0.979798,"lo":null,"hi":null,"n":194,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9401,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9286,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":3,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K4","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K4","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"854260db7eead2e4efbf36b919a9b7944534d93a9994759662c660aa1917922f","measures":[{"category":"all","metric":"oracle_accuracy","value":0.984848,"lo":null,"hi":null,"n":195,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9448,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9296,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":4,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K5","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K5","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"988b10df5c4219190f0a2604f33185476e9b389866c52c22c480460d8c8fd93e","measures":[{"category":"all","metric":"oracle_accuracy","value":0.989899,"lo":null,"hi":null,"n":196,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9441,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9296,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":5,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K6","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K6","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"8a6094ee3da63db103158c41f5c99c92c1aafe3fd11dbb924d7c679e3bad962a","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.93,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9249,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":6,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K7","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K7","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"3218b1b77e48c22a1f553dc71621f8354b42883dc3673ad81ab3c8c49e83dd77","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.931,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9253,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":7,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K8","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K8","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"577deaf94cbdf3bcc54d3fec96883d1201c368e4d0ce4bbbf7d5abae282ceb6f","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9266,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9222,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":8,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-pool-oracle-pool-oracle@K9","benchmark":"enso.gpqa_diamond","split":"test","system":"pool-oracle@K9","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"","store_digest":"","facts_digest":"","commit":"e336832","questions":198,"answered":198,"when":"","ended":"2026-07-23T16:58:13Z","by":"enso-bench","completion":"complete","key":"d87ef196fbc3f9339baa63b1eff869d863b325db3aacb8bd9c7fc510e479f0aa","measures":[{"category":"all","metric":"oracle_accuracy","value":0.994949,"lo":null,"hi":null,"n":197,"of":198},{"category":"all","metric":"best_single_accuracy","value":0.929293,"lo":null,"hi":null,"n":184,"of":198},{"category":"all","metric":"router_heldout_accuracy","value":0.9269,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"champion_relative_heldout_accuracy","value":0.9232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"train_selected_single_heldout_accuracy","value":0.9064,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"arms","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"k","value":9,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-seen-1.6.6-enso","benchmark":"enso.gpqa_diamond","split":"test","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":198,"answered":198,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"e9932648a496c95b74fc9508063565e480310bde06bc09eb80ad9a11fa8b8313","measures":[{"category":"all","metric":"accuracy","value":0.964646,"lo":null,"hi":null,"n":191,"of":198},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":191,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-seen-1.6.6-enso-flash","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-flash","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":198,"answered":198,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"222902e634e406f6d03e890b286271c0b82a4c12013a84e1b809c20053bb1839","measures":[{"category":"all","metric":"accuracy","value":0.954545,"lo":null,"hi":null,"n":189,"of":198},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":189,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-seen-1.6.6-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":null,"max_tokens":null,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"ec4d929f","questions":198,"answered":198,"when":"","ended":"2026-10-16T21:02:49Z","by":"enso-bench","completion":"complete","key":"64380e8ddd46eefd0ed4e7680ca4c02330d48f1a6e3217a955cb9b27c7c9f45e","measures":[{"category":"all","metric":"accuracy","value":0.979798,"lo":null,"hi":null,"n":194,"of":198},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":194,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-deepseek-v4-pro","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-v4-pro","version":"deepseek-v4-pro","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T02:16:55Z","by":"enso-bench","completion":"complete","key":"c4d9db760b1830876509320341493a706443343cd02fea28917a56adaeb3586d","measures":[{"category":"all","metric":"accuracy","value":0.762626,"lo":null,"hi":null,"n":151,"of":198},{"category":"all","metric":"stderr","value":0.0302,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":151,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":52523,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":108318,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":0.2076,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-enso","benchmark":"enso.gpqa_diamond","split":"test","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T02:46:59Z","by":"enso-bench","completion":"complete","key":"9c1583fca7210237c1c8d3ca222e85d90b7c95072f50fa5d9445bccdf085679a","measures":[{"category":"all","metric":"accuracy","value":0.878788,"lo":null,"hi":null,"n":174,"of":198},{"category":"all","metric":"stderr","value":0.0232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":174,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":4.604193,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T04:07:59Z","by":"enso-bench","completion":"complete","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.89899,"lo":null,"hi":null,"n":178,"of":198},{"category":"all","metric":"stderr","value":0.0214,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":178,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":17.9804075,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-fable-5","benchmark":"enso.gpqa_diamond","split":"test","system":"fable-5","version":"anthropic-claude-fable-5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T02:33:53Z","by":"enso-bench","completion":"complete","key":"e55d68c398dba7f168589009bd82f191ed394704dfe71154dd2656a8b635b575","measures":[{"category":"all","metric":"accuracy","value":0.813131,"lo":null,"hi":null,"n":161,"of":198},{"category":"all","metric":"stderr","value":0.0277,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":161,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78121,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":199072,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":3.2204,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-gpt-5.5","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.5","version":"openai-gpt-5.5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T01:54:55Z","by":"enso-bench","completion":"complete","key":"ab5c826e5f694c6e23c7a8635e89356886128f3866e4b76e992002a7a1133a3a","measures":[{"category":"all","metric":"accuracy","value":0.90404,"lo":null,"hi":null,"n":179,"of":198},{"category":"all","metric":"stderr","value":0.0209,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":179,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":54916,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":362128,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":326158,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":3.6899,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"wall_seconds","value":2396.2,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v1-opus-4.8","benchmark":"enso.gpqa_diamond","split":"test","system":"opus-4.8","version":"anthropic-claude-opus-4.8","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-16T01:07:58Z","by":"enso-bench","completion":"complete","key":"d48d792fbad9cc374d6cccc1256df7e0c41ef6652cceb35d281e9001c79ba48b","measures":[{"category":"all","metric":"accuracy","value":0.868687,"lo":null,"hi":null,"n":172,"of":198},{"category":"all","metric":"stderr","value":0.024,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":172,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":78121,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":126069,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":10.627,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"wall_seconds","value":241.3,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-deepseek-3.2","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-3.2","version":"deepseek-3.2","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T20:07:52Z","by":"enso-bench","completion":"complete","key":"527c1b0bf68c985ab40ce3684d2637ae811b0d8cc4d81e074a038d3da3b17973","measures":[{"category":"all","metric":"accuracy","value":0.737374,"lo":null,"hi":null,"n":146,"of":198},{"category":"all","metric":"stderr","value":0.0313,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":146,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":367921,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-deepseek-4-flash","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-4-flash","version":"deepseek-4-flash","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":182,"when":"","ended":"2026-07-19T17:04:56Z","by":"enso-bench","completion":"partial","key":"f45aeeaf7b99783520e7192bbeb5a19fe0e92482453fa26823e37f6c8fc72f00","measures":[{"category":"all","metric":"accuracy","value":0.707071,"lo":null,"hi":null,"n":140,"of":198},{"category":"answered","metric":"accuracy","value":0.769231,"lo":null,"hi":null,"n":140,"of":182},{"category":"all","metric":"stderr","value":0.0323,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":140,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":16,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":16,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":56442,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":101277,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":182,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-deepseek-v4-pro","benchmark":"enso.gpqa_diamond","split":"test","system":"deepseek-v4-pro","version":"deepseek-v4-pro","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T19:39:37Z","by":"enso-bench","completion":"complete","key":"c4d9db760b1830876509320341493a706443343cd02fea28917a56adaeb3586d","measures":[{"category":"all","metric":"accuracy","value":0.752525,"lo":null,"hi":null,"n":149,"of":198},{"category":"all","metric":"stderr","value":0.0307,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":149,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":107808,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":0.2113,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-enso","benchmark":"enso.gpqa_diamond","split":"test","system":"enso","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":196,"when":"","ended":"2026-07-19T20:12:42Z","by":"enso-bench","completion":"partial","key":"9c1583fca7210237c1c8d3ca222e85d90b7c95072f50fa5d9445bccdf085679a","measures":[{"category":"all","metric":"accuracy","value":0.878788,"lo":null,"hi":null,"n":174,"of":198},{"category":"answered","metric":"accuracy","value":0.887755,"lo":null,"hi":null,"n":174,"of":196},{"category":"all","metric":"stderr","value":0.0232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":174,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":2,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":3.2598225,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-enso-flash","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-flash","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-19T19:59:36Z","by":"enso-bench","completion":"complete","key":"bb9043fe09075e92903bb723d2838ca017836eca4b9899b5884df743e1df8d4f","measures":[{"category":"all","metric":"accuracy","value":0.757576,"lo":null,"hi":null,"n":150,"of":198},{"category":"all","metric":"stderr","value":0.0305,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":150,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":0.61722375,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-enso-ultra","benchmark":"enso.gpqa_diamond","split":"test","system":"enso-ultra","version":"","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":198,"when":"","ended":"2026-07-17T13:30:33Z","by":"enso-bench","completion":"complete","key":"f743d011db0dfa103950ce835ba0430f5ccb26e2e3c3c441d6c5c79d0348b80e","measures":[{"category":"all","metric":"accuracy","value":0.90404,"lo":null,"hi":null,"n":179,"of":198},{"category":"all","metric":"stderr","value":0.0209,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":179,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"list_cost_usd","value":17.792357,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-fable-5","benchmark":"enso.gpqa_diamond","split":"test","system":"fable-5","version":"claude-fable-5","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":172,"when":"","ended":"2026-07-19T19:24:01Z","by":"enso-bench","completion":"partial","key":"a04f6e8f21c114b32c21956cfceca66f0c32c338335a8a59da2595e06deb7b3b","measures":[{"category":"all","metric":"accuracy","value":0.813131,"lo":null,"hi":null,"n":161,"of":198},{"category":"answered","metric":"accuracy","value":0.936047,"lo":null,"hi":null,"n":161,"of":172},{"category":"all","metric":"stderr","value":0.0277,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":161,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":26,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":66199,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":1.1751,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-gpt-5.6-luna","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.6-luna","version":"gpt-5.6-luna","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":183,"when":"","ended":"2026-07-19T18:55:16Z","by":"enso-bench","completion":"partial","key":"2aafffcca1ad76050c8282d40af158efc2a2e10e34fbffea6a84b26c3374cf25","measures":[{"category":"all","metric":"accuracy","value":0.828283,"lo":null,"hi":null,"n":164,"of":198},{"category":"answered","metric":"accuracy","value":0.896175,"lo":null,"hi":null,"n":164,"of":183},{"category":"all","metric":"stderr","value":0.0268,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":164,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":15,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":31104,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-gpt-5.6-sol","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.6-sol","version":"gpt-5.6-sol","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":189,"when":"","ended":"2026-07-19T18:32:24Z","by":"enso-bench","completion":"partial","key":"fd799e94ad3e216e5f77621094625282051d543fffa91003752ff22f5e1b93e6","measures":[{"category":"all","metric":"accuracy","value":0.90404,"lo":null,"hi":null,"n":179,"of":198},{"category":"answered","metric":"accuracy","value":0.94709,"lo":null,"hi":null,"n":179,"of":189},{"category":"all","metric":"stderr","value":0.0209,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":179,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":9,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":32702,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-gpt-5.6-terra","benchmark":"enso.gpqa_diamond","split":"test","system":"gpt-5.6-terra","version":"gpt-5.6-terra","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":191,"when":"","ended":"2026-07-19T18:44:24Z","by":"enso-bench","completion":"partial","key":"55c642557f7d6aaebe3cf2cfc43229392c82e9f69bec70043501e324564c48d5","measures":[{"category":"all","metric":"accuracy","value":0.878788,"lo":null,"hi":null,"n":174,"of":198},{"category":"answered","metric":"accuracy","value":0.910995,"lo":null,"hi":null,"n":174,"of":191},{"category":"all","metric":"stderr","value":0.0232,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":174,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":7,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":25529,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true},{"project":"default","id":"enso.gpqa_diamond-test-v2-opus-4.8","benchmark":"enso.gpqa_diamond","split":"test","system":"opus-4.8","version":"claude-opus-4.8","baseline":false,"study":"enso-bench","embedder":"","reader":"","k":null,"temperature":0,"max_tokens":8192,"prompt":"","prompt_digest":"","dataset_digest":"sha256:773e1077b6937cafad702cbeaf0e9b9404ed2125ec3cd4538d94ecd0811708a3","store_digest":"","facts_digest":"","commit":"","questions":198,"answered":196,"when":"","ended":"2026-07-19T19:07:45Z","by":"enso-bench","completion":"partial","key":"4580c668765fd1573cb6c76f6ae9f522991c86ca06d951976ffeeff178c3202f","measures":[{"category":"all","metric":"accuracy","value":0.853535,"lo":null,"hi":null,"n":169,"of":198},{"category":"answered","metric":"accuracy","value":0.862245,"lo":null,"hi":null,"n":169,"of":196},{"category":"all","metric":"stderr","value":0.0251,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"n","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"correct","value":169,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"errors","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"blanks","value":2,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"prompt_tokens","value":60695,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"completion_tokens","value":106384,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"reasoning_tokens","value":0,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"calls","value":198,"lo":null,"hi":null,"n":null,"of":null},{"category":"all","metric":"cost_usd","value":8.8892,"lo":null,"hi":null,"n":null,"of":null}],"notes":"","revision":"original","canonical":true,"visibility":"public","trainable":false,"publishable":true}],"total":63,"completion":{"complete":48,"partial":15,"inconsistent":0,"unknown":0},"gaps":[{"field":"embedder","runs":63},{"field":"facts_digest","runs":63},{"field":"k","runs":63},{"field":"prompt","runs":63},{"field":"prompt_digest","runs":63},{"field":"reader","runs":63},{"field":"store_digest","runs":63},{"field":"when","runs":63},{"field":"commit","runs":38},{"field":"version","runs":36},{"field":"max_tokens","runs":25},{"field":"temperature","runs":25},{"field":"dataset_digest","runs":15}]}