FreshContextA context lab · Fife
Drawing
02 · Benchmarks
Sheet
2 of 3
Rev
A · 2026-10-01

Working drawing 02 · Run log← Benchmarks

Run log.

Every measurement taken, newest first. 616 runs across 17 suites and 160 models, from 2026-08-23 to 2026-09-20.

Runs
616
Distinct graders
30
Incomplete coverage
30

Measurements taken on an Apple M1 Max with 64 GB of unified memory.
Every number here comes from a locked dataset with a recorded grader. Where a measurement is not valid, it is marked rather than removed.

Reading itWhy coverage is shown

A run that scored well on half its cases is not the same as one that scored well on all of them. Collapsing the two hides harness failures inside model results. Where coverage fell below 100 percent it is marked, and those 30 runs should be read as harness problems rather than model performance.

The grader identifier is a hash of the suite source. If it changes between two runs of the same suite, they were not scored by the same code and are not directly comparable.

All runs616 entries · filter, sort, search
FinishedSuiteModelRuntime · profileScoreCoverageGrader · dataset · config
taggertagger/2ornith-35b-taggernot recordedextraction85.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 02e7b350ee762892
needleneedle/1edge0-35bnot recordedextraction62.7%Coverage 110/110g c38dec33aa1c86c2d 5c5199b9eee8a595c cc08042253cc6e13
groundinggrounding/1bonsai2-27b-ptq1not recordedextraction66.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 0407c0f9d876e4a3
epistemicsepistemics/4bonsai2-27b-ptq1not recordedstudy-nothink100.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 9255c41b05f7da62
screeningscreening/1bonsai2-27b-ptq1not recordedextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 2f2913b42c03fae2
worldviewworldview/2bonsai2-27b-ptq1not recordedextraction82.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 40c68eea7655c7e1
screeningscreening/1qwen38-27b-q3kxl-chadnot recordedextraction84.8%Coverage 55% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc e4109198ec0d6a3f
worldviewworldview/2qwen38-27b-q3kxl-chadnot recordedextraction92.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 7f85527901732b16
synthesissynthesis/2qwen38-27b-q3kxl-chadnot recordedextraction85.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c a1f473e0d63ec1b3
worldviewworldview/2bonsai2-27b-ptq1not recordedextraction100.0%Coverage 9/9g 9acfba1b704feb28d e97835de9e6fc227c 40c68eea7655c7e1
toolscaletoolscale/1bonsai2-27b-ptq1not recordedagentic-fast97.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 92433e8a2c1d7275
toolcalltoolcall/1bonsai2-27b-ptq1not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 3e70e301928f2a3d
synthesissynthesis/2bonsai2-27b-ptq1not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 522c48da0b9474a3
nullschemanullschema/1bonsai2-27b-ptq1not recordedextraction31.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 2641ce03c27a545e
groundinggrounding/1bonsai2-27b-pq2not recordedextraction66.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 1685634443e1889f
epistemicsepistemics/4bonsai2-27b-pq2not recordedstudy-nothink100.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 3e65308eee2e3c69
screeningscreening/1bonsai2-27b-pq2not recordedextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 75d8d5feb45c7b60
worldviewworldview/2bonsai2-27b-pq2not recordedextraction82.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 61b04f512aeac639
toolscaletoolscale/1bonsai2-27b-pq2not recordedagentic-fast97.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c c76ee9534d06b617
toolcalltoolcall/1bonsai2-27b-pq2not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c fa07c48a3877570f
synthesissynthesis/2bonsai2-27b-pq2not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 25c89df1304600f0
nullschemanullschema/1bonsai2-27b-pq2not recordedextraction31.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 537688bcd022a4e2
screeningscreening/1qwen3.6-35b-swiftlmnot recordedextraction88.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 7d05a9cf37c57f7c
worldviewworldview/2ornith-35b-a3b-q40-rechecknot recordedextraction85.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 2124361885388e32
screeningscreening/1edge0-35b-rechecknot recordedextraction88.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc f685f626196f2883
screeningscreening/1ternary-bonsai-27b-rechecknot recordedextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc a5afffb46b0e50c4
screeningscreening/1qwen3.8-9b-distill-rechecknot recordedextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4b6dbb06475bbbad
screeningscreening/1gemma4-12b-rechecknot recordedextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 321d8d33ba14ed0c
screeningscreening/1btl-4-q4km-rechecknot recordedextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 86e42deccfe15a63
taggertagger/2minicpm5-2b-q8-nojinjanot recordedextraction76.9%Coverage 99.2% coverageg 63e04d139a0e5ed3d 7ef587bf33e5788ac 0153d351e0ec30ee
taggertagger/2minicpm5-2b-q8-np4-todaynot recordedextraction76.9%Coverage 99.2% coverageg 63e04d139a0e5ed3d 7ef587bf33e5788ac 0d285fb9372dab00
worldviewworldview/2minicpm5-2b-q8-np1not recordedextraction57.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c ff823de24a74e591
synthesissynthesis/2minicpm5-2b-q8-np1not recordedextraction78.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c e59bb419db23bea7
groundinggrounding/1minicpm5-2b-q8-np1not recordedextraction56.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 5ac3f164bce7795b
enrichmentenrichment/3minicpm5-2b-q8-np1not recordedextraction57.4%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 1fb5d909364039d2
tagger_nullabletagger-nullable/1minicpm5-2b-q8-np1not recordedextraction52.9%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 070be56608b35405
screeningscreening/1minicpm5-2b-q8-np1not recordedextraction83.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 12f2ce70461eb2ba
epistemicsepistemics/4minicpm5-2b-q8-np1not recordedstudy-nothink79.2%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc d8638e6e2d8d038b
taggertagger/2minicpm5-2b-q8-np1not recordedextraction76.7%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac c1fd37845b5547c8
worldviewworldview/2minicpm5-2b-exl3not recordedextraction37.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c f0bd4498f4e1a804
synthesissynthesis/2minicpm5-2b-exl3not recordedextraction75.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c d51ee21c635d7430
needleneedle/1minicpm5-2b-exl3not recordedextraction85.5%Coverage 110/110g c38dec33aa1c86c2d 5c5199b9eee8a595c 2b303f0a51347e71
groundinggrounding/1minicpm5-2b-exl3not recordedextraction60.0%Coverage 80% coverageg 30b933dcc6a7e2d4d dcb396faf8b83b0ac deed1276a964eb4d
enrichmentenrichment/3minicpm5-2b-exl3not recordedextraction59.3%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 50da51be20c4e83c
tagger_nullabletagger-nullable/1minicpm5-2b-exl3not recordedextraction46.2%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec dfef0a54e96403a1
taggertagger/2minicpm5-2b-exl3not recordedextraction76.2%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 58ec2a66d452536c
screeningscreening/1minicpm5-2b-exl3not recordedextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 1564c01170861ff4
epistemicsepistemics/4minicpm5-2b-exl3not recordedstudy-nothink81.2%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 18bb944eee207790
tagger_nullabletagger-nullable/1ternary-bonsai-8bnot recordedextraction61.2%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 1a6187eaf0f19f79
taggertagger/2ternary-bonsai-8bnot recordedextraction43.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 1b7169aea80ec684
taggertagger/2ternary-bonsai-8bnot recordedextraction36.4%Coverage 11/11g 63e04d139a0e5ed3d 7ef587bf33e5788ac 1b7169aea80ec684
enrichmentenrichment/3ternary-bonsai-8bnot recordedextraction70.4%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 2449c0a03ec229c7
contractcontract/2ternary-bonsai-8bnot recordedextraction22.9%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c b5bcdf7e22a61983
epistemicsepistemics/4ternary-bonsai-8bnot recordedstudy-nothink72.9%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 22502c57cf79b73d
groundinggrounding/1ternary-bonsai-8bnot recordedextraction51.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac a964482c0a6fefb9
screeningscreening/1ternary-bonsai-8bnot recordedextraction86.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 40d9d3c65e78e666
synthesissynthesis/2ternary-bonsai-8bnot recordedextraction60.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 00939f8fd32a28ff
worldviewworldview/2ternary-bonsai-8bnot recordedextraction37.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 0b08940f0421efe8
nullschemanullschema/1ternary-bonsai-8bnot recordedextraction11.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 409ab3394165e872
toolstools/1ternary-bonsai-8bnot recordedagentic-fast93.3%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c d3347a668da25f1d
toolscaletoolscale/1ternary-bonsai-8bnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 4a4dea00c5224630
toolcalltoolcall/1ternary-bonsai-8bnot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 2ffaff38658dd85a
synthesissynthesis/2minicpm5-2b-exl3not recordedextraction100.0%Coverage 13/13g 4156dd3c13361e8bd 267d1954e225c5b6c c0f3ff2bda3a17e8
worldviewworldview/2minicpm5-2b-exl3not recordedextraction80.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c d413710f2e637004
tagger_nullabletagger-nullable/1edge0-35bnot recordedextraction91.7%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 7b18c32f56523945
taggertagger/2edge0-35bnot recordedextraction88.3%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 7149c1e662a034c9
taggertagger/2edge0-35bnot recordedextraction85.5%Coverage 83/83g 63e04d139a0e5ed3d 7ef587bf33e5788ac 7149c1e662a034c9
synthesissynthesis/2edge0-35bnot recordedextraction81.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 0955df95170a937b
screeningscreening/1edge0-35bnot recordedextraction88.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 60a41f7096ed2f0d
enrichmentenrichment/3edge0-35bnot recordedextraction77.8%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc a0c2477ba575e774
epistemicsepistemics/4edge0-35bnot recordedstudy-nothink97.9%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 63bebcfa1d0c9c54
worldviewworldview/2edge0-35bnot recordedextraction52.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c c4a49113da942eeb
groundinggrounding/1edge0-35bnot recordedextraction89.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac eb1910ec33534645
tagger_nullabletagger-nullable/1minicpm5-2bnot recordedextraction22.9%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 8d6eef850a9bedcc
taggertagger/2minicpm5-2bnot recordedextraction51.7%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 8bc8889aa4bec4ee
enrichmentenrichment/3minicpm5-2bnot recordedextraction59.3%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc a602b52d4aa5d258
contractcontract/2minicpm5-2bnot recordedextraction70.8%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 09ef74ce83b54a17
epistemicsepistemics/4minicpm5-2bnot recordedstudy-nothink77.1%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 8bf3c6f0ca1fa01a
groundinggrounding/1minicpm5-2bnot recordedextraction62.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 8f32a36bd07ac12d
screeningscreening/1minicpm5-2bnot recordedextraction85.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 859326c246bacb4d
synthesissynthesis/2minicpm5-2bnot recordedextraction60.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 602e85a1c355f821
worldviewworldview/2minicpm5-2bnot recordedextraction37.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c d8fc1797ed992595
nullschemanullschema/1minicpm5-2bnot recordedextraction31.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc a792a14d7d990d1b
toolstools/1minicpm5-2bnot recordedagentic-fast93.3%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 29d5dc1655f1e02d
toolscaletoolscale/1minicpm5-2bnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 2400bd439331eb46
toolcalltoolcall/1minicpm5-2bnot recordedextraction73.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c d5030ed4472a8b63
tagger_nullabletagger-nullable/1btl-4-q4kmnot recordedextraction71.3%Coverage 68.3% coverageg 04e875431e26c4b5d db3addf23a2bc4cec 53f41ca547c1a228
tagger_nullabletagger-nullable/1btl-4-q4kmnot recordedextraction71.3%Coverage 164/164g 04e875431e26c4b5d db3addf23a2bc4cec 53f41ca547c1a228
taggertagger/2btl-4-q4kmnot recordedextraction87.1%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 10dcbcd1b3bb7b91
enrichmentenrichment/3btl-4-q4kmnot recordedextraction81.5%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 3b3b53961682ee7f
contractcontract/2btl-4-q4kmnot recordedextraction70.8%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c c5f63e89ad62fa86
chainwalkchainwalk/3btl-4-q4kmnot recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 9b7c71d675210c91
epistemicsepistemics/4btl-4-q4kmnot recordedstudy-nothink100.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 0689f579cb5fa875
groundinggrounding/1btl-4-q4kmnot recordedextraction76.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b6421e71dc1b07d5
screeningscreening/1btl-4-q4kmnot recordedextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc df6b9c70d3ecb99c
synthesissynthesis/2btl-4-q4kmnot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 34ecdb4bf4ded955
worldviewworldview/2btl-4-q4kmnot recordedextraction55.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 7cf929c72ed89ccb
nullschemanullschema/1btl-4-q4kmnot recordedextraction44.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 43c9232ce793d709
toolstools/1btl-4-q4kmnot recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c a04248bbed30bba3
toolscaletoolscale/1btl-4-q4kmnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 83afd32cbd70262a
toolcalltoolcall/1btl-4-q4kmnot recordedextraction93.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 0adbf9c03a0169c7
tagger_nullabletagger-nullable/1btl-4not recordedextraction91.7%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec f9c64867e9dfb91b
taggertagger/2btl-4not recordedextraction85.0%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 81d3e449bf19eaea
enrichmentenrichment/3btl-4not recordedextraction87.0%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 0b71856ba217c91c
contractcontract/2btl-4not recordedextraction64.6%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c bf1f8546a0e1b97c
chainwalkchainwalk/3btl-4not recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 8dbbe23a8427e3bc
epistemicsepistemics/4btl-4not recordedstudy-nothink100.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 438aa2f62c6153af
groundinggrounding/1btl-4not recordedextraction76.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 7d9f8293fd874d62
screeningscreening/1btl-4not recordedextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 8197a1913a41df95
synthesissynthesis/2btl-4not recordedextraction80.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 11c6d6217d23f0b7
worldviewworldview/2btl-4not recordedextraction62.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 0104404569f7c535
nullschemanullschema/1btl-4not recordedextraction36.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 9b2dcb073c569fce
toolstools/1btl-4not recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c e43140ad3e77d008
toolscaletoolscale/1btl-4not recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 962089edc90681de
toolcalltoolcall/1btl-4not recordedextraction76.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 7d3d7741437436e1
tagger_nullabletagger-nullable/1bonsai-27b-1bitnot recordedextraction90.8%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec f3c4a61093079a3e
taggertagger/2bonsai-27b-1bitnot recordedextraction85.4%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac d75dadae6c07b420
tagger_nullabletagger-nullable/1bonsai-27b-mlx2-cortextmlxextraction88.8%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 67cfcfc5c61806c7
taggertagger/2bonsai-27b-mlx2-cortextmlxextraction87.5%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac a7bdc6604033d727
tagger_nullabletagger-nullable/1bonsai-8b-1bitnot recordedextraction41.7%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec d5d5bc2627ca6b54
enrichmentenrichment/3bonsai-27b-1bitnot recordedextraction79.6%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 612035dbfdcf9143
taggertagger/2bonsai-8b-1bitnot recordedextraction28.3%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac e931e287089b3229
contractcontract/2bonsai-27b-1bitnot recordedextraction25.0%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c f3e9344f382b675d
chainwalkchainwalk/3bonsai-27b-1bitnot recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 315259486d2b1e0e
enrichmentenrichment/3bonsai-27b-mlx2-cortextmlxextraction72.2%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc c6981047f9ae77d3
epistemicsepistemics/4bonsai-27b-1bitnot recordedstudy-nothink87.5%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 2f1d2e8b3a422ec6
contractcontract/2bonsai-27b-mlx2-cortextmlxextraction75.0%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 1db1392d6a3fe16b
groundinggrounding/1bonsai-27b-1bitnot recordedextraction67.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 0f1cdb00af0adb60
tagger_nullabletagger-nullable/1bonsai-27b-mlx2-m4promlxextraction89.2%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 29c36e514c29b1c2
screeningscreening/1bonsai-27b-1bitnot recordedextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 06fe499419357acb
enrichmentenrichment/3bonsai-8b-1bitnot recordedextraction61.1%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc e43f51321b57c883
synthesissynthesis/2bonsai-27b-1bitnot recordedextraction35.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c b6b3f7a5739fbaf7
worldviewworldview/2bonsai-27b-1bitnot recordedextraction40.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c c66967b2cb84959c
nullschemanullschema/1bonsai-27b-1bitnot recordedextraction18.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b6bf04bcfeb45185
contractcontract/2bonsai-8b-1bitnot recordedextraction20.8%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c a575849c8bd49029
chainwalkchainwalk/3bonsai-8b-1bitnot recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 6d222e16c742210f
toolstools/1bonsai-27b-1bitnot recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c a9cb56f68c317ce8
toolscaletoolscale/1bonsai-27b-1bitnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 8ee047a8f4681484
epistemicsepistemics/4bonsai-8b-1bitnot recordedstudy-nothink79.2%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc f1ce82d657bdf4e2
groundinggrounding/1bonsai-8b-1bitnot recordedextraction55.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 1ac5570cbae78ecd
screeningscreening/1bonsai-8b-1bitnot recordedextraction86.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 7b113b84e3e9ea89
synthesissynthesis/2bonsai-8b-1bitnot recordedextraction65.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 49c73224f7b988ec
worldviewworldview/2bonsai-8b-1bitnot recordedextraction40.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 1f1610844ef40acb
nullschemanullschema/1bonsai-8b-1bitnot recordedextraction19.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc de1a0f97f9063521
toolstools/1bonsai-8b-1bitnot recordedagentic-fast93.3%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 79e4f8448168d640
toolscaletoolscale/1bonsai-8b-1bitnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 6fc2b443c7d76dde
taggertagger/2bonsai-27b-mlx2-m4promlxextraction87.9%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 821ca1ce68849b25
toolcalltoolcall/1bonsai-27b-1bitnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 0f6815eef83b64d0
toolcalltoolcall/1bonsai-8b-1bitnot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 516c9c0e0de06220
epistemicsepistemics/4bonsai-27b-mlx2-cortextmlxstudy-nothink89.6%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc f8818645d3ba1522
groundinggrounding/1bonsai-27b-mlx2-cortextmlxextraction71.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 4f595a317a905809
screeningscreening/1bonsai-27b-mlx2-cortextmlxextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 64e14fdadbcea0e6
enrichmentenrichment/3bonsai-27b-mlx2-m4promlxextraction72.2%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc e41b038c77c413b8
synthesissynthesis/2bonsai-27b-mlx2-cortextmlxextraction66.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c a3e244ab46faf1d3
contractcontract/2bonsai-27b-mlx2-m4promlxextraction75.0%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 5836be70b11516a5
worldviewworldview/2bonsai-27b-mlx2-cortextmlxextraction42.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 88e5e9056622def0
toolstools/1bonsai-27b-mlx2-cortextmlxagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 8c56b2e4e619015f
toolscaletoolscale/1bonsai-27b-mlx2-cortextmlxagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c bf7830ad8b1e5adb
toolcalltoolcall/1bonsai-27b-mlx2-cortextmlxextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 072e0651b5a1976c
chainwalkchainwalk/3bonsai-27b-mlx2-m4promlxagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 16fb378c7bf6e96a
tagger_nullabletagger-nullable/1ternary-bonsai-27bnot recordedextraction90.0%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 29960d736fce3ea5
taggertagger/2ternary-bonsai-27bnot recordedextraction85.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 773ed13c720ca034
enrichmentenrichment/3ternary-bonsai-27bnot recordedextraction72.2%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc 075725332e318d6b
epistemicsepistemics/4bonsai-27b-mlx2-m4promlxstudy-nothink89.6%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 3c03af0d96b59518
contractcontract/2ternary-bonsai-27bnot recordedextraction75.0%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c e5777a35ca1e5f10
groundinggrounding/1bonsai-27b-mlx2-m4promlxextraction71.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 86fb3d4c7b477c6c
chainwalkchainwalk/3ternary-bonsai-27bnot recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 078f17fd21ba7d57
screeningscreening/1bonsai-27b-mlx2-m4promlxextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4082207a1256c4b6
synthesissynthesis/2bonsai-27b-mlx2-m4promlxextraction66.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 14f4738d0f91fc84
worldviewworldview/2bonsai-27b-mlx2-m4promlxextraction42.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c a4f61e2b7e694288
toolstools/1bonsai-27b-mlx2-m4promlxagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 98ea18969989ee4e
toolscaletoolscale/1bonsai-27b-mlx2-m4promlxagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 52e205dd25e5567b
epistemicsepistemics/4ternary-bonsai-27bnot recordedstudy-nothink85.4%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 321e00a36a5faaeb
groundinggrounding/1ternary-bonsai-27bnot recordedextraction68.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 3b0afe72fb0c0121
toolcalltoolcall/1bonsai-27b-mlx2-m4promlxextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 8e73d545a7ffd2aa
screeningscreening/1ternary-bonsai-27bnot recordedextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c5097500538c3719
synthesissynthesis/2ternary-bonsai-27bnot recordedextraction66.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 6a368a22cfb7fb02
worldviewworldview/2ternary-bonsai-27bnot recordedextraction42.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 3a4970c1d0eed32d
nullschemanullschema/1ternary-bonsai-27bnot recordedextraction27.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 004a863515b30c86
toolstools/1ternary-bonsai-27bnot recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 7f71a1d06f005b6d
toolscaletoolscale/1ternary-bonsai-27bnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 13185468aa0f107f
toolcalltoolcall/1ternary-bonsai-27bnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 7dece85f852d6798
tagger_nullabletagger-nullable/1qwen3.8-9b-distillnot recordedextraction90.0%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec d7923863e8b56e76
taggertagger/2qwen3.8-9b-distillnot recordedextraction83.3%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac d2642a91c9a03367
enrichmentenrichment/3qwen3.8-9b-distillnot recordedextraction79.6%Coverage 54/54g b51222c2ca38cfdfd 75361864baa727abc d537736901f01a81
contractcontract/2qwen3.8-9b-distillnot recordedextraction25.0%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 5a052624057c52ff
chainwalkchainwalk/3qwen3.8-9b-distillnot recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 43d9a11df6da4927
epistemicsepistemics/4qwen3.8-9b-distillnot recordedstudy-nothink89.6%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc a0e9adc5c6542d53
groundinggrounding/1qwen3.8-9b-distillnot recordedextraction67.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 696fd8b30eed53f0
screeningscreening/1qwen3.8-9b-distillnot recordedextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 5ac25f36beb78f8c
synthesissynthesis/2qwen3.8-9b-distillnot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 8481e2a6e1f3e60c
worldviewworldview/2qwen3.8-9b-distillnot recordedextraction40.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 6a67c959e17c98f5
nullschemanullschema/1qwen3.8-9b-distillnot recordedextraction18.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 56c7dc8f982d59d3
toolstools/1qwen3.8-9b-distillnot recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 2411d23420a9fcb7
toolscaletoolscale/1qwen3.8-9b-distillnot recordedagentic-fast100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 13a2f2f87c9bcdc8
toolcalltoolcall/1qwen3.8-9b-distillnot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 2cd02d2d291d660a
epistemicsepistemics/4qwen3.5-4b-basenot recordedstudy-nothink85.4%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 211ae40d03020e0e
tagger_nullabletagger-nullable/1qwen3.5-4b-basenot recordedextraction93.8%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 50a352dbe249d795
worldviewworldview/2qwen3.5-4b-basenot recordedextraction40.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 314d1643f96e91a9
groundinggrounding/1qwen3.5-4b-basenot recordedextraction74.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 0f7dbcd0b1d1afd4
nullschemanullschema/1qwen3.5-4b-basenot recordedextraction33.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 8ed6c2d36dcf6e58
toolscaletoolscale/1qwen3.5-4b-basenot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 634f8ac324d31747
toolcalltoolcall/1qwen3.5-4b-basenot recordedextraction36.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c abdddca6a1cde4d9
epistemicsepistemics/4neohorse-1-4bnot recordedstudy-nothink75.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc a4f7cdc18f2e769e
tagger_nullabletagger-nullable/1neohorse-1-4bnot recordedextraction86.2%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 78196673fb9772d8
worldviewworldview/2neohorse-1-4bnot recordedextraction40.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 0ca5e9b594862393
groundinggrounding/1neohorse-1-4bnot recordedextraction63.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b382340e2e3ad6fa
nullschemanullschema/1neohorse-1-4bnot recordedextraction27.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc e55e57d062c38080
toolscaletoolscale/1neohorse-1-4bnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c b90d64d3c6c193a5
toolcalltoolcall/1neohorse-1-4bnot recordedextraction56.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c e018b8e820715109
needleneedle/1ornith-9b-kv-q40not recordedextraction55.5%Coverage 110/110g c38dec33aa1c86c2d 5c5199b9eee8a595c 09bf0b1e19047eb2
needleneedle/1ornith-9b-kv-f16not recordedextraction58.2%Coverage 110/110g c38dec33aa1c86c2d 5c5199b9eee8a595c 72650e0b4ba22c6c
synthesissynthesis/2gemma4-12b-b10893not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 41030e0a832a129e
epistemicsepistemics/4ornith-1.5-9bnot recordedextraction100.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 54cc298fd20d22af
contractcontract/2ornith-1.5-9bnot recordedextraction68.8%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 1bf634506e78523a
synthesissynthesis/2ornith-1.5-9bnot recordedextraction80.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 3fba7b7b697d2bc6
nullschemanullschema/1glm-4.7-flash-q40not recordedextraction44.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc a206ab6679bc0fed
epistemicsepistemics/4glm-4.7-flash-q40not recordedextraction75.0%Coverage 48/48g acf84972a0ad5f38d 4bce453fd376553cc 0550121d973797df
worldviewworldview/2glm-4.7-flash-q40not recordedextraction37.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 9d24f8d5c84a9e2e
synthesissynthesis/2glm-4.7-flash-q40not recordedextraction60.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c b33ed27337b5ef7e
toolscaletoolscale/1glm-4.7-flash-q40not recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 5383698d8f3d7c82
toolcalltoolcall/1glm-4.7-flash-q40not recordedextraction38.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c f492f0f6a7e78f98
toolcalltoolcall/1ornith-9b-kvq4not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 970506005273665a
groundinggrounding/1ornith-9b-kvq4not recordedextraction80.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 4c61ed44aed10e7a
nullschemanullschema/1ornith-9b-kvq4not recordedextraction56.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 32a57cca965b6777
worldviewworldview/2ornith-35b-a3b-q40not recordedextraction85.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 36403d17c401159a
groundinggrounding/1ornith-35b-a3b-q40not recordedextraction76.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 95c69b1144e96db8
nullschemanullschema/1ornith-35b-a3b-q40not recordedextraction36.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 4324ac01a6993c44
contractcontract/2ornith-35b-a3b-q40not recordedextraction66.7%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c 16c1587da02e495a
toolscaletoolscale/1ornith-35b-a3b-q40not recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 9ed2b4b41dc68126
toolcalltoolcall/1ornith-35b-a3b-q40not recordedextraction80.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 9391215fff65e4b5
worldviewworldview/2ornith-1.5-9bnot recordedextraction62.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c ce57d773fcc0cbcd
groundinggrounding/1ornith-1.5-9bnot recordedextraction81.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 4a6ad96362484d18
nullschemanullschema/1ornith-1.5-9bnot recordedextraction52.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 0dd3a4ce0c1655b8
toolscaletoolscale/1ornith-1.5-9bnot recordedextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 8105ecbc4488d189
toolcalltoolcall/1ornith-1.5-9bnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c c2191a274d61789c
tagger_nullabletagger-nullable/1gpt-oss-20b-study-defaultnot recordedstudy-default93.9%Coverage 94.3% coverageg 04e875431e26c4b5d db3addf23a2bc4cec 7649f91ca5eb87a4
nullschemanullschema/1gpt-oss-20bnot recordedextraction72.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 262a6f5122bb9bbd
taggertagger/2gpt-oss-20bnot recordedextraction86.2%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac b9bd7f33427388fd
tagger_nullabletagger-nullable/1gpt-oss-20bnot recordedextraction85.7%Coverage 99.2% coverageg 04e875431e26c4b5d db3addf23a2bc4cec acb0e0e0f1883336
nullschemanullschema/1qwen35-9b-mlx-mxfp4mlxextraction34.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc da30e30743dadebe
nullschemanullschema/1qwen35-9b-mlx-affine-g32mlxextraction45.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 4cb05505e1d4b652
nullschemanullschema/1qwen35-9b-mlx-affine-g64mlxextraction59.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 987f7b78b76a6a60
nullschemanullschema/1qwen35-9b-gguf-q40not recordedextraction6.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc e5fa21270174a387
nullschemanullschema/1qwen35-9b-gguf-q4kmnot recordedextraction23.6%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 71580a34709d8143
synthesissynthesis/2qwen3.8-27b-q4_0not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 7bca9c0f60cfafa3
nullschemanullschema/1qwen3.8-27b-q4_0not recordedextraction69.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 0464331c99998f53
worldviewworldview/2qwen3.8-27b-q4_0not recordedextraction80.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 4fb569ecc91140c9
toolscaletoolscale/1qwen3.8-27b-q4_0not recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 7dedd451e841393d
toolcalltoolcall/1qwen3.8-27b-q4_0not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c ce7aa224f6d8c444
nullschemanullschema/1k2-36b-Q4_1not recordedextraction50.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc a1e412de2582e21b
nullschemanullschema/1k2-36b-Q5_1not recordedextraction58.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 6e470ceac8f4401c
nullschemanullschema/1k2-36b-Q5_0not recordedextraction56.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 53f943deaafde391
synthesissynthesis/2k2-36b-q4_0not recordedextraction76.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 4bc7f1a68df72179
nullschemanullschema/1k2-36b-q4_0not recordedextraction65.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc c71d223f0ac921ec
worldviewworldview/2k2-36b-q4_0not recordedextraction57.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c d2167f66564312b7
toolscaletoolscale/1k2-36b-q4_0not recordedextraction90.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 5467852ddcdb11c6
toolcalltoolcall/1k2-36b-q4_0not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 646dbb2eca06be4d
toolcalltoolcall/1reap-60b-mlx-4bit-uniformmlxextraction-t0728.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c d696a3a98ce65e4f
toolcalltoolcall/1reap-60b-4bit-repronot recordedextraction25.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 9fc8dc4dd468ed18
synthesissynthesis/2reap-60b-mlx-4bit-uniformmlxextraction85.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 5f382a39bf24731a
nullschemanullschema/1reap-60b-mlx-4bit-uniformmlxextraction84.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 52349074a17dc8f5
worldviewworldview/2reap-60b-mlx-4bit-uniformmlxextraction47.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 76804a68d58c5eb6
toolscaletoolscale/1reap-60b-mlx-4bit-uniformmlxextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c a58faee14a0f3ed6
toolcalltoolcall/1reap-60b-mlx-4bit-uniformmlxextraction25.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 9fc8dc4dd468ed18
synthesissynthesis/2diffusiongemma-26b-mlxmlxextraction80.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 6220b53efc9f35b4
worldviewworldview/2diffusiongemma-26b-mlxmlxextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c b0b19b278db1058f
toolscaletoolscale/1diffusiongemma-26b-mlxmlxextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 40a7e393e161d98f
toolcalltoolcall/1diffusiongemma-26b-mlxmlxextraction5.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 49640f29f7104a95
synthesissynthesis/2reap-60b-gguf-q4kmnot recordedextraction81.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 5d5c05e03d9c61e2
VOID-degenerate-nullschemanullschema/1reap-60b-gguf-q4kmnot recordedextraction100.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b923bc8484d5f158
worldviewworldview/2reap-60b-gguf-q4kmnot recordedextraction80.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 361b96fbc9be289c
toolscaletoolscale/1reap-60b-gguf-q4kmnot recordedextraction87.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 437c75c01b4063cd
toolcalltoolcall/1reap-60b-gguf-q4kmnot recordedextraction41.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 4faf8950bd5037a5
synthesissynthesis/2reap-60b-20260910not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 078d5fad4e6d0a0f
nullschemanullschema/1reap-60b-20260910not recordedextraction47.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 067da0ca87821991
worldviewworldview/2reap-60b-20260910not recordedextraction47.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c a9d79c1de500e4b4
toolscaletoolscale/1reap-60b-20260910not recordedextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c ce60a8f4e40a948a
toolcalltoolcall/1reap-60b-20260910not recordedextraction78.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c d3a58130e11b1504
synthesissynthesis/2spark-x25-4bnot recordedextraction28.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c ffe0798e394ad2c2
nullschemanullschema/1spark-x25-4bnot recordedextraction48.6%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 080b2b956a3c69aa
worldviewworldview/2spark-x25-4bnot recordedextraction20.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 7eb3a5699dc38e49
toolscaletoolscale/1spark-x25-4bnot recordedextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 266788017096e178
toolcalltoolcall/1spark-x25-4bnot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c bd8238a4b2ea134b
worldviewworldview/2qwen38-rebase-b10893not recordedextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 90bd067cd59ed0c2
nullschemanullschema/1qwen38-rebase-b10893not recordedextraction76.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 317df1bd5861fa04
worldviewworldview/2k2-36b-q8-precisionnot recordedextraction55.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c c95b13073128b76a
nullschemanullschema/1k2-36b-q8-precisionnot recordedextraction70.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 3a41a0a4d5f18851
worldviewworldview/2k2-7b-bf16-precisionnot recordedextraction30.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 1705a034b7c84210
nullschemanullschema/1k2-7b-bf16-precisionnot recordedextraction37.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc d931535c0ebf24a6
worldviewworldview/2k2-7b-q8-precisionnot recordedextraction30.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c e20e4b1b964fa50d
nullschemanullschema/1k2-7b-q8-precisionnot recordedextraction36.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc ed643e52a40b0e33
worldviewworldview/2k2-7b-q4-precisionnot recordedextraction37.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 3bbb4039e7a64a8b
nullschemanullschema/1k2-7b-q4-precisionnot recordedextraction37.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 577908cfcedc7d78
synthesissynthesis/2k2-4b-bf16-precisionnot recordedextraction56.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 0faa5511a9576d51
nullschemanullschema/1k2-4b-bf16-precisionnot recordedextraction43.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 776fc6d33aa8cc34
worldviewworldview/2k2-4b-bf16-precisionnot recordedextraction50.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 770c2ce3d2f16e96
toolscaletoolscale/1k2-4b-bf16-precisionnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c e21f6ac8887f7f5d
toolcalltoolcall/1k2-4b-bf16-precisionnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 2c2e5971d9f6382f
synthesissynthesis/2k2-3.7b-q8-precisionnot recordedextraction56.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 3529bab4b75f7502
nullschemanullschema/1k2-3.7b-q8-precisionnot recordedextraction43.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 807203bd18193834
worldviewworldview/2k2-3.7b-q8-precisionnot recordedextraction50.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c f654ce7b2d1ac877
toolscaletoolscale/1k2-3.7b-q8-precisionnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 1eedcfdecea95e86
toolcalltoolcall/1k2-3.7b-q8-precisionnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c ddb3ca71c12850c5
synthesissynthesis/2k2-3.7b-q4-precisionnot recordedextraction50.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 49e024d8aab08569
nullschemanullschema/1k2-3.7b-q4-precisionnot recordedextraction38.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b4a841d2cc241d1f
worldviewworldview/2k2-3.7b-q4-precisionnot recordedextraction52.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 324471b050d0453b
toolscaletoolscale/1k2-3.7b-q4-precisionnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 8bb7dfa4a8ce435f
toolcalltoolcall/1k2-3.7b-q4-precisionnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 9c699af63ecd43af
synthesissynthesis/2gemma4-12b-midrangenot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 480148dc413153dc
nullschemanullschema/1gemma4-12b-midrangenot recordedextraction87.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc c10333ca24baf0ea
worldviewworldview/2gemma4-12b-midrangenot recordedextraction97.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 4bbaa37911174c88
toolscaletoolscale/1gemma4-12b-midrangenot recordedextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c bf8723aa88c0d4b7
toolcalltoolcall/1gemma4-12b-midrangenot recordedextraction55.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 57bdac944281e060
synthesissynthesis/2lfm25-8b-a1b-midrangenot recordedextraction53.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 089fdc592c6d831d
nullschemanullschema/1lfm25-8b-a1b-midrangenot recordedextraction27.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b3d59631a0a0785e
worldviewworldview/2lfm25-8b-a1b-midrangenot recordedextraction30.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 717aaa5a6a785c10
toolscaletoolscale/1lfm25-8b-a1b-midrangenot recordedextraction82.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 4727b9e997fb1a2e
toolcalltoolcall/1lfm25-8b-a1b-midrangenot recordedextraction1.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 3b306a765082433d
synthesissynthesis/2qwen3-8b-midrangenot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 07092184bce46ed0
nullschemanullschema/1qwen3-8b-midrangenot recordedextraction34.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 5fdc1502f911a148
worldviewworldview/2qwen3-8b-midrangenot recordedextraction45.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 39d8f0df5c0c0e6f
toolscaletoolscale/1qwen3-8b-midrangenot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c d27e6f32d963b586
toolcalltoolcall/1qwen3-8b-midrangenot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c c341d6e4665581b5
PARTIAL-KILLED-nullschemanullschema/1qwen38-vendor-qwen-thinknot recordedvendor-qwen-think56.2%Coverage 16/16g d7448e0f5fc3f9afd 3b91280bb40372efc e25e7e28827fd589
worldviewworldview/2qwen38-vendor-qwen-thinknot recordedvendor-qwen-think77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c e78fad9e97d45282
synthesissynthesis/2qwen38-gsqrco-iq3snot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 92ea3b5723445268
nullschemanullschema/1qwen38-gsqrco-iq3snot recordedextraction62.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 62838af8410253c2
worldviewworldview/2qwen38-gsqrco-iq3snot recordedextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 624bd85753786f4e
toolscaletoolscale/1qwen38-gsqrco-iq3snot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 3177b556489558c1
toolcalltoolcall/1qwen38-gsqrco-iq3snot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c d08352bc157ff4d3
synthesissynthesis/2bonsai-27b-ternarynot recordedextraction66.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c ef7f6527771769a7
nullschemanullschema/1bonsai-27b-ternarynot recordedextraction27.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 204142d8636f4fc2
worldviewworldview/2bonsai-27b-ternarynot recordedextraction42.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 121caa6718989cf9
toolscaletoolscale/1bonsai-27b-ternarynot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 83edc9129d9d77cd
toolcalltoolcall/1bonsai-27b-ternarynot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c b3a241de7392ea56
toolscaletoolscale/1k2-36b-np1not recordedextraction87.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 6e72c541e7fd804e
toolcalltoolcall/1k2-36b-np1not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c f4f31defced2ec18
synthesissynthesis/2qwen38-27b-np1not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 2867e80b35de0e49
nullschemanullschema/1qwen38-27b-np1not recordedextraction76.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 458eb55eee2cc3a3
worldviewworldview/2qwen38-27b-np1not recordedextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c cf60f4eb1ae532f8
toolscaletoolscale/1qwen38-27b-np1not recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 2b5ec5e83a2c8961
toolcalltoolcall/1qwen38-27b-np1not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 7019f408382de810
nullschemanullschema/1k2-36b-vendor-k2bnot recordedvendor-k2b57.7%Coverage 98.6% coverageg d7448e0f5fc3f9afd 3b91280bb40372efc 62630cca2615a18f
synthesissynthesis/2k2-36b-vendor-k2bnot recordedvendor-k2b90.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 19ff3eed9d7b1a47
worldviewworldview/2k2-36b-vendor-k2bnot recordedvendor-k2b82.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c d16f8472c1b1d87d
synthesissynthesis/2k2-36b-vendor-k2not recordedvendor-k293.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c b7e765413a3dd2f2
nullschemanullschema/1k2-36b-vendor-k2not recordedvendor-k248.6%Coverage 97.2% coverageg d7448e0f5fc3f9afd 3b91280bb40372efc 80a8857ae078d242
worldviewworldview/2k2-36b-vendor-k2not recordedvendor-k277.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c e6f5010ab18f79e7
synthesissynthesis/2k2-36b-extractionnot recordedextraction75.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c b92607640a462939
nullschemanullschema/1k2-36b-extractionnot recordedextraction54.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 5e938f4fe9784ee9
worldviewworldview/2k2-36b-extractionnot recordedextraction52.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 9cc504b6f261a5b3
chainwalkchainwalk/3k2-36b-ctx128k-q8not recordedextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c b3aa4c4b6efce314
worldviewworldview/2k2-36b-ctx128k-q8not recordedextraction65.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 082b24620003bf78
synthesissynthesis/2k2-36b-ctx32knot recordedextraction70.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 7873f3430a2f042e
toolscaletoolscale/1k2-36b-ctx32knot recordedextraction90.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c b2321bc042bae630
toolcalltoolcall/1k2-36b-ctx32knot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 3b6cfef3b606fe07
chainwalkchainwalk/3k2-36b-ctx32knot recordedextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c b3aa4c4b6efce314
screeningscreening/1k2-36b-ctx32knot recordedextraction90.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc af55e22558068ab0
nullschemanullschema/1k2-36b-ctx32knot recordedextraction54.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 345de57f0f3a686f
worldviewworldview/2k2-36b-ctx32knot recordedextraction65.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 082b24620003bf78
worldviewworldview/2k2-36b-a4b-q4not recordedextraction78.9%Coverage 19/19g 9acfba1b704feb28d e97835de9e6fc227c 082b24620003bf78
synthesissynthesis/2k2-36b-a4b-q4not recordedextraction73.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 7873f3430a2f042e
toolscaletoolscale/1k2-36b-a4b-q4not recordedextraction90.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c b2321bc042bae630
toolcalltoolcall/1k2-36b-a4b-q4not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 3b6cfef3b606fe07
worldviewworldview/2k2-7bnot recordedextraction30.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c e229d76d7d696757
worldviewworldview/2k2-3.7bnot recordedextraction50.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 13dc41ad1b2821d9
worldviewworldview/2gemma4-12bnot recordedextraction97.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 585e7383f726d519
worldviewworldview/1reap-60bnot recordedextraction47.5%Coverage 40/40g d511b635ce7bbfd3d d7ae9cbb38fafbe9c f6b9a462ff423a87
synthesissynthesis/2gemma4-12bnot recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c dea865f1d077f0d8
synthesissynthesis/2k2-7bnot recordedextraction75.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c d3f015ffb0c32d4d
synthesissynthesis/2k2-3.7bnot recordedextraction58.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c be9a405fa957d750
synthesissynthesis/2reap-60bnot recordedextraction81.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 6e88592c339b65ea
synthesissynthesis/1gemma4-12bnot recordedextraction80.0%Coverage 60/60g 27df090db4445c2cd 760936a5348b2ffdc 9749137aeec83ad6
synthesissynthesis/1k2-7bnot recordedextraction75.0%Coverage 60/60g 27df090db4445c2cd 760936a5348b2ffdc 58c73d3c88ebea78
synthesissynthesis/1k2-3.7bnot recordedextraction86.7%Coverage 60/60g 27df090db4445c2cd 760936a5348b2ffdc cc272a124c5d1351
synthesissynthesis/1qwen3-next-80b-reap-mlx-mixed36mlxextraction100.0%Coverage 60/60g 27df090db4445c2cd 760936a5348b2ffdc 93c5f1d3b8c8e17c
chainwalkchainwalk/3k2-horizon-3.7bnot recordedextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 497e8e74501f9a9e
nullschemanullschema/1k2-horizon-3.7bnot recordedextraction43.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc c1cd134c67de1621
screeningscreening/1k2-horizon-3.7bnot recordedextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 5d3e0bfbb30467e0
toolstools/1k2-horizon-3.7bnot recordedextraction86.7%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 4b2e40f5222213ec
toolscaletoolscale/1k2-horizon-3.7bnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 4535019c467a8444
toolcalltoolcall/1k2-horizon-3.7bnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c f848b35c571d582e
toolstools/1k2-horizon-7bnot recordedextraction100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c d1b260004a9b283e
chainwalkchainwalk/3k2-horizon-7bnot recordedextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c ce69ff4b8656191d
toolscaletoolscale/1k2-horizon-7bnot recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 62b1c628753b16b6
groundinggrounding/1k2-horizon-7bnot recordedextraction55.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 30ddb902b06a0c00
nullschemanullschema/1k2-horizon-7bnot recordedextraction34.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 54f9df9571bc16e8
screeningscreening/1k2-horizon-7bnot recordedextraction90.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc e92045e24be569c7
contractcontract/2k2-horizon-7bnot recordedextraction22.9%Coverage 48/48g cc2d23c5bae45474d 1fe53d30cb5480f6c e127d0663cbe7e98
toolcalltoolcall/1k2-horizon-7bnot recordedextraction95.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 93ba527fea40c309
screeningscreening/1granite-guardian-4.1-8b-mlx-bf16mlxextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 081a28b5708d9572
screeningscreening/1granite-guardian-4.1-8b-mlx-q8mlxextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 764b495364f3e7ff
screeningscreening/1granite-guardiannot recordedextraction36.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c
screeningscreening/1granite-guardian-4.1-8b-mlx-mixed36mlxextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 1e2bab38313786db
screeningscreening/1guardian-mixed36-mlxlmmlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc b56b3c67a8112f7f
screeningscreening/1granite-guardiannot recordedextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc fe46fd4c1301cd33
screeningscreening/1granite-guardiannot recordedextraction100.0%Coverage 41/41g 0661b49a10be2d2ad 64c97ca2269c29afc fe46fd4c1301cd33
screeningscreening/1granite-guardian-gguf-q4kmnot recordedextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8
screeningscreening/1granite-guardiannot recordedextraction37.3%Coverage 59/59g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c
screeningscreening/1granite-guardian-gguf-q4kmnot recordedextraction100.0%Coverage 36/36g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8
screeningscreening/1granite-guardiannot recordedextraction40.0%Coverage 5/5g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c
screeningscreening/1granite-guardian-gguf-q4kmnot recordedextraction100.0%Coverage 33/33g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8
screeningscreening/1granite-guardian-mlx-mixed36mlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc d9be4d5a49d0f4d5
toolcalltoolcall/1qwen3-next-80b-reapnot recordedextraction35.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c e9925436d57909a1
toolcalltoolcall/1gemma4-e2bnot recordedextraction0.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 022b5819dd82ff96
toolcalltoolcall/1granite-4.2-30bnot recordedextraction20.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c bf1109eb4e492a3d
toolcalltoolcall/1qwen3.6-35bnot recordedextraction65.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 8e5c69081ab588b0
toolcalltoolcall/1qwen3.8-27bnot recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c ac125d630f2b70bc
toolcalltoolcall/1mlx-community-Qwen3.6-35B-A3B-4bitmlxextraction60.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 4a82e7591c905bf0
toolcalltoolcall/1qwen3-next-80b-reap-mlx-mixed36mlxextraction78.3%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 8352ab9b62086e37
toolcalltoolcall/1qwen3.8-27b-mlx-4bitmlxextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 8886d10bc276895c
contractcontract/2mlx-community-Qwen3.6-35B-A3B-4bitmlxextraction27.1%Coverage 48/48g 486601ba23034dd6d 1fe53d30cb5480f6c 4fc6c3fdb9c9b02c
contractcontract/2q36-toolparsernot recordedextractionn/aCoverage 0% coverageg 486601ba23034dd6d 1fe53d30cb5480f6c 2225a59526198b68
screeningscreening/1mlx-community-Qwen3.6-35B-A3B-4bitmlxextraction90.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4ed45f89d9eca30b
screeningscreening/1qwen3.8-27b-mlx-4bitmlxextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 1b2a598c6ef11638
contractcontract/2qwen3.8-27b-mlx-4bitmlxextraction75.0%Coverage 48/48g 486601ba23034dd6d 1fe53d30cb5480f6c 2750a525d9018a88
contractcontract/2flashnext-4.27bpw-m64not recordedextractionn/aCoverage 0% coverageg 486601ba23034dd6d 1fe53d30cb5480f6c 92b28699e44d08e7
contractcontract/2qwen3-next-80b-reapnot recordedextractionn/aCoverage 0% coverageg 486601ba23034dd6d 1fe53d30cb5480f6c cbb517440b51fc70
contractcontract/2qwen3-next-80b-reap-mlx-mixed36mlxextraction54.2%Coverage 48/48g 486601ba23034dd6d 1fe53d30cb5480f6c e059879c3195b24c
contractcontract/1qwen3-next-80b-reap-mlx-q4mlxextraction47.2%Coverage 36/36g 2dd146852463f032d ab4bb33923bd0ed6c 14fac1620eb065e0
screeningscreening/1qwen3-next-80b-reap-mlx-q4mlxextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 72e18625ddbdaf10
screeningscreening/1qwen3-next-80b-reap-mlx-mixed36mlxextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c37510db6b5ff9cf
contractcontract/1reapq4-mlx_lmmlxextractionn/aCoverage 0% coverageg 2dd146852463f032d ab4bb33923bd0ed6c 224bdfd4a5d2e672
screeningscreening/1reapq4-mlx_lmmlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc 2f64770a4290f344
contractcontract/1reapmix36-rapid-mlxmlxextractionn/aCoverage 0% coverageg 2dd146852463f032d ab4bb33923bd0ed6c 46d4a279b80fca4d
screeningscreening/1reapmix36-rapid-mlxmlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc 8077358e07c7af36
contractcontract/1reapq4-rapid-mlxmlxextractionn/aCoverage 0% coverageg 2dd146852463f032d ab4bb33923bd0ed6c 788a11f836a3345b
screeningscreening/1reapq4-rapid-mlxmlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc ba21b624ebdf49bd
contractcontract/1granite-4.2-30bnot recordedextraction66.7%Coverage 36/36g 2dd146852463f032d ab4bb33923bd0ed6c cc8ca71e6e299aee
contractcontract/1gemma4-12bnot recordedextraction66.7%Coverage 36/36g 2dd146852463f032d ab4bb33923bd0ed6c 0d1de531e8b00c72
chainwalkchainwalk/3flashnext-4.27bpw-m64not recordedagentic-fast0.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 17c29ba75eeadc76
screeningscreening/1flashnext-4.27bpw-m64not recordedextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 028bac48a65abdd9
nullschemanullschema/1flashnext-4.27bpw-m64not recordedextraction58.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc a1f73dd74c73dbc6
groundinggrounding/1flashnext-4.27bpw-m64not recordedextraction81.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 2867d56b04f8bbb4
chainwalkchainwalk/3qwen3-next-80b-reap-agnot recordedagentic-fast50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c ccae884465959abc
toolscaletoolscale/1qwen3-next-80b-reap-agnot recordedagentic-fast90.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 2b03adebd9317650
toolstools/1qwen3-next-80b-reap-agnot recordedagentic-fast100.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 3907525a897ced43
nullschemanullschema/1qwen3-next-80b-reapnot recordedextraction97.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc cc55008d40e60573
groundinggrounding/1qwen3-next-80b-reapnot recordedextraction87.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 7e1bbf58551d87ef
screeningscreening/1qwen3-next-80b-reapnot recordedextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 81efb9eaae394534
screeningscreening/1glm-4.7-flash-mlx-mixed_4_6mlxextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c1b73af4ac52ca1f
screeningscreening/1glm-4.7-flash-mlx-mixed_3_6mlxextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 99894ae40745ad56
groundinggrounding/1muse-glimmer-30bllama.cppextraction85.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac d9d25da365e04cc8
screeningscreening/1muse-glimmer-30bllama.cppextraction86.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 63338a6fdcbdcddd
screeningscreening/1laguna-xs2-mlx-q4mlxextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc 3c17fa93e654c0b4
nullschemanullschema/1glm-4.7-flash-mlx-q4mlxextraction40.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b669c85bfa68b0b5
groundinggrounding/1glm-4.7-flash-mlx-q4mlxextraction53.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 2432689cc6751eea
screeningscreening/1glm-4.7-flash-mlx-q4mlxextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c80ceb72756eafac
nullschemanullschema/1glm-4.7-flash-mlx-q8mlxextraction59.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 97ef09a912feb8be
groundinggrounding/1glm-4.7-flash-mlx-q8mlxextraction76.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 6d0a345ab4ecfa54
screeningscreening/1glm-4.7-flash-mlx-q8mlxextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc b4008e66dcadf553
nullschemanullschema/1qwen3-8b-mlx-8bitmlxextraction56.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b9aaca6eee78b218
groundinggrounding/1qwen3-8b-mlx-8bitmlxextraction74.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac e34a89daf5181d58
screeningscreening/1qwen3-8b-mlx-8bitmlxextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 02039a8c6b78a23b
nullschemanullschema/1nemotron-lightning-30b-mlx-4bitmlxextraction9.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 023ab1ea82fce0de
groundinggrounding/1nemotron-lightning-30b-mlx-4bitmlxextraction56.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 15a43d7b2024f68c
screeningscreening/1nemotron-lightning-30b-mlx-4bitmlxextraction90.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 813491de8103980c
nullschemanullschema/1granite-4.2-30b-ggufllama.cppextraction90.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc ad5177ffa2d55fa5
groundinggrounding/1granite-4.2-30b-ggufllama.cppextraction84.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac e353f603986dcdcd
screeningscreening/1granite-4.2-30b-ggufllama.cppextraction98.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 001987450ecbaa8a
nullschemanullschema/1ornith-1.5-35b-mlx-4bitmlxextraction62.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 1fb1a5ad2ee784e3
groundinggrounding/1ornith-1.5-35b-mlx-4bitmlxextraction67.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac a438aff9707ec8a1
screeningscreening/1ornith-1.5-35b-mlx-4bitmlxextraction88.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4f3b9812298e963e
nullschemanullschema/1granite-4.2-30b-mlx-q4mlxextraction100.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 48b3d526e6d6e6a3
VOID-degenerate-nullschemanullschema/1granite-4.2-30b-mlx-q4mlxextraction100.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 48b3d526e6d6e6a3
groundinggrounding/1granite-4.2-30b-mlx-q4mlxextraction86.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac db0a9174aa469c68
screeningscreening/1granite-4.2-30b-mlx-q4mlxextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc f71ccbbb16cd8099
shapegenshapegen/2qwen3-coder-30bllama.cppextraction0.0%Coverage 12/12g f23222ad8df22fd8d fc27d4e1a999c675c cbf6852b8edc0984
sitebuildsitebuild/1qwen3-coder-30bllama.cppagentic-fast0.0%Coverage 1/1g b2c603d6c0d6afb3d 8b54725d2778dc60c 0cac83c8fbc03eec
tagger_nullabletagger-nullable/1tagger-e2b-v1-dl-tagger-e2b-v1llama.cppextraction75.0%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec b0015c0679b3c9f8
taggertagger/2tagger-e2b-v1-dl-tagger-e2b-v1llama.cppextraction74.2%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 26b77eacaf1fc207
tagger_nullabletagger-nullable/1gemma4-e2b-mlx-4bitmlxextraction73.8%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec d40c89a4c0ded16e
taggertagger/2gemma4-e2b-mlx-4bitmlxextraction85.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 1623b2cdd0ccbfaf
nullschemanullschema/1qwen3-next-80b-mlx-4bitmlxextraction95.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc d1b64a4d48cff9ef
screeningscreening/1qwen3-next-80b-mlx-4bitmlxextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 22413c6aa05bedb0
groundinggrounding/1qwen3-next-80b-mlx-4bitmlxextraction87.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 0c539d39afff5bd1
groundinggrounding/1qwen3.8-27b-noreasonllama.cppextraction80.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 4a3b4b7c53219329
groundinggrounding/1qwen3.8-27b-mlx-4bitmlxextraction92.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 42a3cf291ff302bb
chainwalkchainwalk/3qwen-agentworld-35bllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c c4305e58879e2b40
chainwalkchainwalk/3qwen3-next-80b-agllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 3a96fdcc21129ae7
chainwalkchainwalk/3qwen3.6-35b-agllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c ea9f2c30d07a149b
chainwalkchainwalk/3qwen3.6-35b-agllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c ea9f2c30d07a149b
toolscaletoolscale/1qwen3.6-35b-agllama.cppextraction80.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c f995b25bd0b360cf
toolstools/1qwen3.6-35b-agllama.cppextraction93.3%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c a8b21b992370e7c6
chainwalkchainwalk/3qwen3-next-80b-agllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c 3a96fdcc21129ae7
toolscaletoolscale/1qwen3-next-80b-agllama.cppextraction95.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 18366d2ac6e48e7c
toolstools/1qwen3-next-80b-agllama.cppextraction93.3%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c 91dcd2c830490d0e
chainwalkchainwalk/3qwen-agentworld-35bllama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c c4305e58879e2b40
toolscaletoolscale/1qwen-agentworld-35bllama.cppextraction72.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c edcc1fd1f9bd35f0
toolstools/1qwen-agentworld-35bllama.cppextraction80.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c e56fd9e9b9103b0a
screeningscreening/1granite-guardian-3.1-2bllama.cppextraction0.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c3bc4d1194d50b4b
nullschemanullschema/1qwen38-flash-nextllama.cppextraction50.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc d248e89da830ce31
screeningscreening/1qwen38-flash-nextllama.cppextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc dd9b4d06d5abee09
groundinggrounding/1qwen38-flash-nextllama.cppextraction79.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 9148fcdc2bc14fe4
nullschemanullschema/1nemotron-lightning-30bllama.cppextraction15.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 8f3225e9b30dcc6b
screeningscreening/1nemotron-lightning-30bllama.cppextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc bd58c270aedc9f3d
groundinggrounding/1nemotron-lightning-30bllama.cppextraction60.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f734b41b3caabfdd
nullschemanullschema/1qwen3-next-80bllama.cppextraction97.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 5913b00d3e8c6b3d
screeningscreening/1qwen3-next-80bllama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c
groundinggrounding/1qwen3-next-80bllama.cppextraction88.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f34a40087b318cc6
tagger_nullabletagger-nullable/1qwen3-next-80b-tagllama.cppextraction90.4%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec c033312a94ce8bbe
taggertagger/2qwen3-next-80b-tagllama.cppextraction93.3%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac bb9d18596364b9f4
tagger_nullabletagger-nullable/1qwen3.6-35b-tagllama.cppextraction92.5%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 2f1c411d3dd00d20
taggertagger/2qwen3.6-35b-tagllama.cppextraction90.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 336518ff1b1d0973
tagger_nullabletagger-nullable/1gemma4-12b-b10618llama.cppextraction97.9%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec e947bd43665a9bdb
taggertagger/2gemma4-12b-b10618llama.cppextraction93.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac c947e8a080eadfe2
screeningscreening/1granite-guardian-4.1-8bllama.cppextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 9ba7cd65a17e6418
nullschemanullschema/1lfm2.5-8b-a1bllama.cppextraction27.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 00612fdd4a39faf4
groundinggrounding/1lfm2.5-8b-a1bllama.cppextraction47.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 90be8dffe935ab41
screeningscreening/1lfm2.5-8b-a1bllama.cppextraction73.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 2cbf094131c24516
nullschemanullschema/1qwen3-next-80b-coderllama.cppextraction56.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 74810b0cff4603b3
screeningscreening/1qwen3-next-80b-coderllama.cppextraction90.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc e7b3303ff47f6803
groundinggrounding/1qwen3-next-80b-coderllama.cppextraction76.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 140e26c8be639be7
nullschemanullschema/1qwen3.6-35bllama.cppextraction61.1%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 7a652a6a84f42ef5
screeningscreening/1qwen3.6-35bllama.cppextraction86.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4246ff56e771b097
groundinggrounding/1qwen3.6-35bllama.cppextraction82.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 279f3a4bd1ff0c7e
groundinggrounding/1qwen3.6-35bllama.cppextraction86.3%Coverage 73/73g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 279f3a4bd1ff0c7e
groundinggrounding/1qwen3-next-80b-thinkingllama.cppstudy-default100.0%Coverage 1/1g 30b933dcc6a7e2d4d dcb396faf8b83b0ac cb1f0b0a42b6ac48
nullschemanullschema/1qwen3-next-80b-thinkingllama.cppextraction58.3%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 8f8aa14bba9f91c3
screeningscreening/1qwen3-next-80b-thinkingllama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 4320932025e05e5d
groundinggrounding/1qwen3-next-80b-thinkingllama.cppextraction65.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac e644b21297e6198b
nullschemanullschema/1qwen3-next-80bllama.cppextraction97.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 5913b00d3e8c6b3d
screeningscreening/1qwen3-next-80bllama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c
groundinggrounding/1qwen3-next-80bllama.cppextraction88.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f34a40087b318cc6
nullschemanullschema/1qwen3-next-80b-a3b-iq4xsllama.cppextraction97.2%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 860f8678b21dfb1f
screeningscreening/1qwen3-next-80b-a3b-iq4xsllama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc c6cb8e26e5eec1ec
groundinggrounding/1qwen3-next-80b-a3b-iq4xsllama.cppextraction88.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac e3b83bfa70c1a417
groundinggrounding/1qwen3-next-80b-a3b-iq4xs-smokellama.cppextraction73.9%Coverage 92% coverageg 30b933dcc6a7e2d4d dcb396faf8b83b0ac e6920f17163814d7
nullschemanullschema/1glm-4.7-flash-q8llama.cppextraction48.6%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 3d836e2b73f9cd77
screeningscreening/1glm-4.7-flash-q8llama.cppextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc b7d076058290ae5f
groundinggrounding/1glm-4.7-flash-q8llama.cppextraction76.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f7116f1eb6a7f001
nullschemanullschema/1glm-4.7-flash-q8llama.cppextractionn/aCoverage 0% coverageg d7448e0f5fc3f9afd 3b91280bb40372efc 3d836e2b73f9cd77
screeningscreening/1glm-4.7-flash-q8llama.cppextractionn/aCoverage 0% coverageg 0661b49a10be2d2ad 64c97ca2269c29afc b7d076058290ae5f
nullschemanullschema/1qwen3.5-122b-a10b-iq3llama.cppextraction45.8%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 5e7cd3243c74ce98
screeningscreening/1qwen3.5-122b-a10b-iq3llama.cppextraction88.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 45dab17de7814804
groundinggrounding/1qwen3.5-122b-a10b-iq3llama.cppextraction80.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b3059734754cd76c
nullschemanullschema/1agents-a1-35b-b10618llama.cppextraction38.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 9a9ee4f1853f385a
screeningscreening/1agents-a1-35b-b10618llama.cppextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc fe6603a03488c606
groundinggrounding/1agents-a1-35b-b10618llama.cppextraction71.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b6d15c86cef9c0f6
nullschemanullschema/1qwen3-coder-30b-b10618llama.cppextraction37.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc ffb75533d79bc27d
screeningscreening/1qwen3-coder-30b-b10618llama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 01f8fd00f78cb299
groundinggrounding/1qwen3-coder-30b-b10618llama.cppextraction76.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 85522d05c3671c16
nullschemanullschema/1qwen3.5-9b-q8-b10618llama.cppextraction30.6%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 989a2b1d084c0c53
screeningscreening/1qwen3.5-9b-q8-b10618llama.cppextraction96.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 6c6da4df0333507c
groundinggrounding/1qwen3.5-9b-q8-b10618llama.cppextraction72.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 9e54265c33ff0f82
nullschemanullschema/1gemma4-12b-b10618llama.cppextraction88.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 2c03d6ebad98fccc
screeningscreening/1gemma4-12b-b10618llama.cppextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 79323c88f8e515df
groundinggrounding/1gemma4-12b-b10618llama.cppextraction84.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac ba97a71cfa0468a7
nullschemanullschema/1gemma4-e2b-b10618llama.cppextraction12.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 38b4b96050d74d17
screeningscreening/1gemma4-e2b-b10618llama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 80f542cbf88cfba7
groundinggrounding/1gemma4-e2b-b10618llama.cppextraction61.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b18ad353c84d839e
nullschemanullschema/1gemma4-e4b-b10618llama.cppextraction13.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 84794dc91d0ce3b4
screeningscreening/1gemma4-e4b-b10618llama.cppextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc b75251f174426f4d
groundinggrounding/1gemma4-e4b-b10618llama.cppextraction62.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac dc6988d619b065bf
nullschemanullschema/1ornith-1.5-35b-q6-b10618llama.cppextraction34.7%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 355fd8b860ca54b1
screeningscreening/1ornith-1.5-35b-q6-b10618llama.cppextraction95.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc ce44f5f606a0131e
groundinggrounding/1ornith-1.5-35b-q6-b10618llama.cppextraction72.8%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac bc2f7777482c6fb6
nullschemanullschema/1devstral-small-2-24b-b10618llama.cppextraction62.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 836a74186efb247a
screeningscreening/1devstral-small-2-24b-b10618llama.cppextraction100.0%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc d8a2ef703d82163d
groundinggrounding/1devstral-small-2-24b-b10618llama.cppextraction79.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac ed588aa2abdb41ef
screeningscreening/1gemma4-12bllama.cppextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc b7d605769821c0d8
nullschemanullschema/1gemma4-12bllama.cppextraction88.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc ec3358e6aa5e1088
screeningscreening/1gemma4-e4bllama.cppextraction93.3%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 824bef7dab174615
nullschemanullschema/1gemma4-e4bllama.cppextraction13.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc addbcab5facddd0b
screeningscreening/1gemma4-e2bllama.cppextraction91.7%Coverage 60/60g 0661b49a10be2d2ad 64c97ca2269c29afc 905fc96bd8c3e874
nullschemanullschema/1gemma4-e2bllama.cppextraction12.5%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc e268490afdec64ce
tagger_nullabletagger-nullable/1gemma4-12b-abllama.cppextraction97.9%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 8bf8e2bee9ac7333
taggertagger/2gemma4-12b-abllama.cppextraction93.8%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 3c8ef5d04a11b585
tagger_nullabletagger-nullable/1gemma4-e2b-abllama.cppextraction90.4%Coverage 240/240g 04e875431e26c4b5d db3addf23a2bc4cec 23e712860bee6d0e
taggertagger/2gemma4-e2b-abllama.cppextraction91.2%Coverage 240/240g 63e04d139a0e5ed3d 7ef587bf33e5788ac 4619919ac18affd5
groundinggrounding/1qwen3-coder-30bllama.cppextraction77.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac ade06bde17b71832
groundinggrounding/1qwen3.8-27bllama.cppextraction80.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 1d989a6b00eb212c
groundinggrounding/1agents-a1-35bllama.cppextraction71.2%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 3cb35299a047efb8
groundinggrounding/1qwen3.5-9b-q8llama.cppextraction72.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac bd21ebb86ee6f863
groundinggrounding/1gemma4-12bllama.cppextraction84.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 31241ed46ed4d6a5
groundinggrounding/1gemma4-e4bllama.cppextraction62.4%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 267624907124ed7e
groundinggrounding/1gemma4-e2bllama.cppextraction61.6%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac dee67653e2de45c6
taggertagger/2qwen3.8-iq1sllama.cppstudy-nothink31.6%Coverage 44.2% coverageg 956e03bbffa79aa4d 7ef587bf33e5788ac f6700e17f70a9c2a
epistemicsepistemics/4qwen3.8-iq1sllama.cppstudy-nothink77.1%Coverage 72.9% coverageg 2a2f7e4e90d6dd63d 4bce453fd376553cc 4bfecdedff811923
toolstools/1qwen3.8-iq1sllama.cppagentic-fast76.9%Coverage 86.7% coverageg d6a32c09e57bea7bd 33a44812f0ad4c39c 02e356bf0012eaf2
enrichmentenrichment/3qwen3.8-iq1sllama.cppstudy-nothink60.5%Coverage 79.6% coverageg 7d661b93852b5ffdd 75361864baa727abc 11d22e9108889bce
chainwalkchainwalk/3qwen3.8-iq1sllama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c e2e5d225bbfe60d6
chainwalkchainwalk/3gemma4-12b-r3llama.cppagentic-fast50.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 2cbb0e64811ac557
chainwalkchainwalk/3gemma4-e4b-r3llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 7e97acd7556a3909
chainwalkchainwalk/3gemma4-e2b-r3llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 24f4c1683cfb7a85
chainwalkchainwalk/3gemma4-12b-r2llama.cppagentic-fast50.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c e1a3cdf8d371cae6
chainwalkchainwalk/3gemma4-e4b-r2llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c ec61f0c3716fc3f8
chainwalkchainwalk/3gemma4-e2b-r2llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 277579259f233168
toolscaletoolscale/1agents-a1-35bllama.cppagentic-fast100.0%Coverage 40/40g 1bae1f3e1b606eaed b24abb108c409178c f55610aeacd8ae8c
chainwalkchainwalk/3gemma4-12b-r1llama.cppagentic-fast50.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 97645e44ce72b737
toolscaletoolscale/1gemma4-12bllama.cppagentic-fast90.0%Coverage 40/40g 1bae1f3e1b606eaed b24abb108c409178c 42412bb32a456ced
toolscaletoolscale/1gemma4-e4bllama.cppagentic-fast100.0%Coverage 40/40g 1bae1f3e1b606eaed b24abb108c409178c 64d002411f012d3c
toolscaletoolscale/1gemma4-e2bllama.cppagentic-fast100.0%Coverage 40/40g 1bae1f3e1b606eaed b24abb108c409178c 3860ab39a73cff08
chainwalkchainwalk/3gemma4-e4b-r1llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 7ef98c4a8fe4369b
chainwalkchainwalk/3gemma4-e2b-r1llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c 92c0ac5ca29b9cdc
epistemicsepistemics/4qwen3.8-27bllama.cppstudy-nothink100.0%Coverage 48/48g 2a2f7e4e90d6dd63d 4bce453fd376553cc 541a385213b500cb
toolstools/1qwen3.8-27bllama.cppagentic-fast100.0%Coverage 15/15g d6a32c09e57bea7bd 33a44812f0ad4c39c 35475e0c17bfc385
enrichmentenrichment/3gemma4-12bllama.cppstudy-nothink77.8%Coverage 54/54g 7d661b93852b5ffdd 75361864baa727abc 5367be2a63165de3
enrichmentenrichment/3gemma4-e4bllama.cppstudy-nothink70.4%Coverage 54/54g 7d661b93852b5ffdd 75361864baa727abc 60945fac08964a72
enrichmentenrichment/3gemma4-e2bllama.cppstudy-nothink75.9%Coverage 54/54g 7d661b93852b5ffdd 75361864baa727abc 94079faf08beb84b
epistemicsepistemics/4agents-a1-35bllama.cppstudy-nothink100.0%Coverage 48/48g 2a2f7e4e90d6dd63d 4bce453fd376553cc 2101ffcef80989dc
toolstools/1agents-a1-35bllama.cppagentic-fast100.0%Coverage 15/15g d6a32c09e57bea7bd 33a44812f0ad4c39c 555c28b5386478f6
epistemicsepistemics/4gemma4-12bllama.cppstudy-nothink100.0%Coverage 48/48g 2a2f7e4e90d6dd63d 4bce453fd376553cc b6ac24eba6a83a5d
epistemicsepistemics/4gemma4-e4bllama.cppstudy-nothink97.9%Coverage 48/48g 2a2f7e4e90d6dd63d 4bce453fd376553cc 37147fa352af2d7a
epistemicsepistemics/4gemma4-e2bllama.cppstudy-nothink68.8%Coverage 48/48g 2a2f7e4e90d6dd63d 4bce453fd376553cc e5abf1e2bbe8c2c8
chainwalkchainwalk/2gemma4-12bllama.cppagentic-fast50.0%Coverage 2/2g 48abd22e0117fddad 129a9e74408c8919c b4834ee71de7e834
chainwalkchainwalk/2gemma4-e4bllama.cppagentic-fast0.0%Coverage 2/2g 48abd22e0117fddad 129a9e74408c8919c 8e18e895c23f4485
chainwalkchainwalk/2gemma4-e2bllama.cppagentic-fast0.0%Coverage 2/2g 48abd22e0117fddad 129a9e74408c8919c eef56b755300de59
toolstools/1gemma4-e2bllama.cppagentic-fast100.0%Coverage 15/15g d6a32c09e57bea7bd 33a44812f0ad4c39c 33f8efb324ad39aa
toolstools/1gemma4-12bllama.cppagentic-fast86.7%Coverage 15/15g d6a32c09e57bea7bd 33a44812f0ad4c39c b34ee497223231c8
toolstools/1gemma4-e4bllama.cppagentic-fast100.0%Coverage 15/15g d6a32c09e57bea7bd 33a44812f0ad4c39c 50b166f799c52d51
taggertagger/2gemma4-12bllama.cppstudy-nothink93.2%Coverage 80.3% coverageg 28983856e4bf2dd9d 7ef587bf33e5788ac d10e58be49cb1d55
taggertagger/2gemma4-e4bllama.cppstudy-nothink90.8%Coverage 50% coverageg 28983856e4bf2dd9d 7ef587bf33e5788ac 60e6c55236269057
taggertagger/2gemma4-e2bllama.cppstudy-nothink91.2%Coverage 240/240g 28983856e4bf2dd9d 7ef587bf33e5788ac 72d758d807701d51
taggertagger-e2b-v1llama.cppextraction77.1%Coverage 240/240g —d —c —