Coding (general)

Results are only compared within a matching group, so a model tested one way is never ranked against a model tested another way.

Rank coding models and agents on general software tasks: code generation, repository-level SWE, and terminal work

Ranking groups use separate scales. Compare configurations only inside the same group; EvalRank never flattens unlike systems into one leaderboard.

ベンチマーク横断のコンセンサス

このトピックで採用されているベンチマーク全体でモデルを順位付けしたものです。意思決定のときと同じ重み付けを用いています。各スコアは、モデルの結果が最高結果に占める割合です。

RankModelShare of bestBenchmarks
1claudeopus55100.0%2
2claudefable5191.2%2
3gpt61sol88.2%2
4gemini4argon87.7%2
5claudesonnet5587.0%2
6claudefable580.7%2
7claudeopus578.8%2
8gpt61terra75.7%1
9GPT-5.6 Sol72.5%2
10gpt6sol71.9%2
11grok4765.6%2
12claudeopus4860.4%2
13grok-4.657.1%2
14gpt56terra55.2%2
15kimi-k353.6%2
16gemini38flash52.8%2
17gemini37flash49.2%2
18gpt6luna48.2%2
19claudesonnet547.2%2
20GPT-5.6 Luna45.3%2
21deepseek-v4-flash-073131.5%2

エージェントシステム · エージェンティック

Exploratory - not a ranked winner yet
rg-coding-general-agent-system-agentic-agent-system-v1

エクスプローラーのエビデンス

DeepSWE

Sources differ; shown separately, never averaged。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1gpt-6-astra mini_swe_agent_gpt_6_astra_xhighconfig_bbf07a11592b85abcf998b2bab14c636111bf22c2a0f135a859fc4637b64e74074%不明1
2gemini-3-8-flash mini_swe_agent_gemini_3_8_flash_highconfig_99f1f5a4baf710ee887184f3528382eb054e0afecf3559ac86b34d460c87300474%不明1
3claude-opus-5 mini_swe_agent_claude_opus_5_maxconfig_c647489700452c2c208a35693bed018b306c90d50da186a9291b35eb188e22bd74%不明1
4gpt-6-astra mini_swe_agent_gpt_6_astra_maxconfig_40b1c572d64c805933bcf2129f08dc144572e516dae4925b339fef491870b07273%不明1
5gpt-6-astra mini_swe_agent_gpt_6_astra_highconfig_faa515a61e9b4ae933ed9ffafbc09b61632eef8431566e5075943695de9224b173%不明1
6claude-opus-5 mini_swe_agent_claude_opus_5_xhighconfig_907c7158813ee95155a6b16492e69cab72740d132a672b18e7917e6f54d3c52b73%不明1
7claude-opus-5 mini_swe_agent_claude_opus_5_highconfig_334f3a9751b1488836c3ca0b198a3ea0fd3e40bb457a88a406f18607209fa2b273%不明1
8gpt-6-astra mini_swe_agent_gpt_6_astra_mediumconfig_d07b34ffb2af2531251a46451b40bd8518b18b6de158362a3781709c5f81964773%不明1
9gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_maxconfig_d275cb2c69e7afc4d9080fc5284f0decdd56f860104fd44fe1829806ddf651de73%不明1
10gemini-3-8-flash mini_swe_agent_gemini_3_8_flash_mediumconfig_945e3c0a75cfab73b288951d2693331a0d4c93d3c38bce63058186ce60a58a7a71%不明1
11gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_xhighconfig_5f5d92ae1a6bf9da591422530bfcd4acfeaa5aec7bdfb8a90395f8fddd4f9ccb71%不明1
12claude-fable-5 mini_swe_agent_claude_fable_5_xhighconfig_bf246640f0460734fd45a96c676710109e2690cd919b520e6b18ec9c85079fe870%不明1
13claude-fable-5 mini_swe_agent_claude_fable_5_maxconfig_6cd82db3623f359522ba12352bb5ff95b9cc92eb9e09a24ce83a2acda8dfeba270%不明1
14gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_maxconfig_d7a3c6ced6dc428983ae9afd107ebd99d1e29da0322e8767df8159c22229b4b570%不明1
15gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_highconfig_a9772d655df076b0c7d85604222b8ccb822d70a46403bc9f8cf8b3b160b0e22369%不明1
16glm-5-3 mini_swe_agent_glm_5_3_maxconfig_cd2676556edf9dfcda2adb6d7a9cd4a1a7330a4af6059b87d5727b7eb1ca7af669%不明1
17claude-opus-5 mini_swe_agent_claude_opus_5_mediumconfig_820e8e67840338ad87da9a6120ed79d7238e33b22778298914022e04a4cf161769%不明1
18claude-fable-5 mini_swe_agent_claude_fable_5_highconfig_04bb50f778bf6bf2c8169e378e0f045a45ffcdf91a637eeabe35a44fde13539b69%不明1
19kimi-k3 mini_swe_agent_kimi_k3_maxconfig_7f7bf933eb0fa4a7ec5d62cfdeb29a8484d66dd1dc39d28e27ee6b3de50ff0e069%不明1
20grok-4-6 mini_swe_agent_grok_4_6_mediumconfig_2b66a38fe21328d0521612421ff12f5d1eba6a8a6a80563ed1d40a0dbd05ef3667%不明1
21gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_maxconfig_499ebda077ee18c6bf8c3721552206ee3cf90dba0cef0d561bb06daca56dfc1067%不明1
22gpt-6-astra mini_swe_agent_gpt_6_astra_lowconfig_aba7c3968834f0ad1b0b5c15825bedfbc6814f23f4f0be4d06ae4a62141cb39b67%不明1
23gpt-5-5 mini_swe_agent_gpt_5_5_xhighconfig_c13865a4ec6a39ff87177d09fb544d8eb4712f9966e2a74b8e4d4e9b735a21c667%不明1
24grok-4-6 mini_swe_agent_grok_4_6_xhighconfig_43454ebde0853f40bb6c1b12f8900ea3545996192365102ab5e67608f1b8095167%不明1
25gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_mediumconfig_b94b69cafe5ee03f283577664e74caa7e342e6133d663688f179d7a5a50b7a5765%不明1
26claude-fable-5 mini_swe_agent_claude_fable_5_mediumconfig_61b63ec56d8b6ea22a200a5fb3de9729acfff57a3a3beab1aac7a34ae034694065%不明1
27gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_highconfig_6a8634d1604a9f757490bb8f8fdbdbffe54e6b04fa34b93a825ce1c0de92511c65%不明1
28grok-4-6 mini_swe_agent_grok_4_6_highconfig_162a581cb5c40d58417136a2856b1bbc5515aab288e49dd66579bd04a315e52e65%不明1
29gpt-5-5 mini_swe_agent_gpt_5_5_highconfig_59053425417061eb762aefd1b03f50dbf187f5e10da5a8b7ed19b790b86d285064%不明1
30glm-5-3-flash mini_swe_agent_glm_5_3_flash_maxconfig_599d6845c9eb4e3e89bbe917ac21d48dba8d197a374968fd4928f74bfa5479d563%不明1
31deepseek-v4-pro mini_swe_agent_deepseek_v4_pro_maxconfig_f64966d7e89784334403b1fe7878048a57ec00876ce000c6e2bef57e5f49e12963%不明1
32gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_mediumconfig_402a0fe4d6931565bf6724561c4061f0e88fbda3bf95b56c133f6d26addc3e2661%不明1
33gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_xhighconfig_dc7c67793df85a38e322ab4feed92a231902a67745d1e268a87b6d74844d0cf460%不明1
34claude-fable-5 mini_swe_agent_claude_fable_5_lowconfig_c690e0be3e8d248bcf56f308c253ff9ce8c149333a1e0b9412b7f8b69a31bf2660%不明1
35claude-opus-4-8 mini_swe_agent_claude_opus_4_8_maxconfig_b8895eb0c759293b55e37def7cfbd162f10b78486bc0ef5c0f3f3ae9f43a2cd959%不明1
36claude-opus-5 mini_swe_agent_claude_opus_5_lowconfig_24f98c7e7848fa148f57009a6900cbf5074c5e1300c950add2e15db88b435f8858%不明1
37qwen3-8-max mini_swe_agent_qwen3_8_max_xhighconfig_c1fa762bbc21726067c3e67bb1d9481c18268022c7090f2f890f8d514d0fb6bf57%不明1
38gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_xhighconfig_48bad74b1f6da89e03e6d0c75f872d8113fda707e64044512e74e758057407a357%不明1
39muse-spark-1-2 mini_swe_agent_muse_spark_1_2_xhighconfig_7a7ee985e6fe340f164c16d1afb470467960e81f08fbf6f4e65f09676eeba5ae55%不明1
40claude-opus-4-8 mini_swe_agent_claude_opus_4_8_xhighconfig_f08e8f48d01893af79c2caf089122161b3b14c03f77e05d67371c272cb310f0a54%不明1
41gpt-5-5 mini_swe_agent_gpt_5_5_mediumconfig_1ecbed94580896d44ec01b4b99dc0303b3195e94f9691c141b2e9be484d15bb654%不明1
42claude-sonnet-5 mini_swe_agent_claude_sonnet_5_maxconfig_64c1c487db75b6f50cb78e47cbcddc475d7835163bb54bca197d6929807213d854%不明1
43grok-4-5 mini_swe_agent_grok_4_5_highconfig_49cbd80643e492e0cf6b291292344090b910a525752717066aa166b49500ac8654%不明1
44gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_highconfig_c70b094bd6bc90f6d73ca68f68464bf0e93f7fd41ac12ef19f50588add27630154%不明1
45gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_lowconfig_fdac9250de689f25b6718a003882c23c28bf84dd32fa6062f085cdf90e67035254%不明1
46muse-spark-1-1 mini_swe_agent_muse_spark_1_1_xhighconfig_4f26f586de8723346aea4ac6f12834d5725a7817c0cb25377abf7b5b8174defb53%不明1
47deepseek-v4-flash mini_swe_agent_deepseek_v4_flash_maxconfig_ce541a8d1b086c6ec893f0b97904e6a6f35cc3d5f6cef04816ef487c188a8ca153%不明1
48claude-opus-4-8 mini_swe_agent_claude_opus_4_8_highconfig_58680d3eedd4aba4a66e8640af75742e54aafc7acb432a3cadbbf57a588317dc52%不明1
49gpt-5-4 mini_swe_agent_gpt_5_4_xhighconfig_c3464a0472feb8d3fe258f92ca0c657b38233a78d3fc984651940d33f20e86e652%不明1
50claude-sonnet-5 mini_swe_agent_claude_sonnet_5_xhighconfig_147bff69a94abfbdafc928e0bcd0a5e0b29af262312f804505a6afa320b38f0f50%不明1
51claude-opus-4-8 mini_swe_agent_claude_opus_4_8_mediumconfig_3ef8a78571b4db55102a1dcd4c752a5383675e978fe3b4a95498f5bd487d1cbc49%不明1
52claude-sonnet-5 mini_swe_agent_claude_sonnet_5_highconfig_4efd185eb4ad5275b557bc6111ae1947e9488c0690c30b536246c759b66e552c48%不明1
53gemini-3-6-flash mini_swe_agent_gemini_3_6_flash_highconfig_66464aef80070e91183f432938fb0720c862586f4cec7a311ddb916898fe624847%不明1
54gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_lowconfig_b35e7084f490107ff26755c5b1273537c783262b505c1aa482e22478c164c84645%不明1
55gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_highconfig_7ca720abbeb6b966e08ff13e43dd66c4ce24f20cd0c21e347365f9737c3310d044%不明1
56glm-5-2 mini_swe_agent_glm_5_2_maxconfig_08c75ff5b5fae701d4ee71ec5fc3cb6e2a39054e1b28350e64566658218b85e444%不明1
57grok-4-6 mini_swe_agent_grok_4_6_lowconfig_b3887dfd53e7b98841d8c2f592a9e9ed2dd78f42de43dcde2110cb3b91e9762442%不明1
58claude-opus-4-8 mini_swe_agent_claude_opus_4_8_lowconfig_9a1325eb982ef5a1595ffad514abac5e163d6885bbbc075eba16dec0b46f4a4d41%不明1
59claude-sonnet-5 mini_swe_agent_claude_sonnet_5_mediumconfig_f0e2c73135d5b86f49948a23ee64ac435abb667458e1fae9d1c11c8e1186ffa840%不明1
60glm-5-2 mini_swe_agent_glm_5_2_highconfig_f17ac834afbf2b11b522ae81b1ca7f2447e312733af1a89d601b356c3f4af9b136%不明1
61gemini-3-5-flash mini_swe_agent_gemini_3_5_flash_highconfig_0eefe519e147a16e978da082c66fa969726579aeb56973768ca73cb1bc3e21e536%不明1
62gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_mediumconfig_038eeba65e62059f4ecbf181a3fc6b650197e5565b870690ab4acdf99359159535%不明1
63kimi-k2-7-code mini_swe_agent_kimi_k2_7_code_defaultconfig_124cbcc3be53e10cd1eacf75752b42bdb1de1e3f300505cd9a91c8d7cfb62da131%不明1
64claude-sonnet-5 mini_swe_agent_claude_sonnet_5_lowconfig_2ff43d430d17fc22211a61f924364e79392742a599234cff2b758071d0f776d431%不明1
65claude-sonnet-4-6 mini_swe_agent_claude_sonnet_4_6_highconfig_7a7d2700f41f08a7c77f117fa2528b852375d1ff9cd7edc244a6758602df8aca30%不明1
66gpt-5-5 mini_swe_agent_gpt_5_5_lowconfig_eddf24c4f45fdddd638382b42b744f61680535d051dea5acdeb9da97262471d027%不明1
67gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_lowconfig_bd9280382f7291b715a8d59bd21f92caca736754aea139b7257112f4d58b1a5824%不明1
68gemini-3-1-pro-preview mini_swe_agent_gemini_3_1_pro_preview_highconfig_5ab1cfce9a0ab268f572bfcda041482ea856d2d71f2155ab18a1fed803987d6d12%不明1
69gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_mediumconfig_6f12c6f06fbb79da94ca98267c419407731951297057e438fbfed83e8fac354d11%不明1
70gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_lowconfig_4c1aa5736b934cbb1c18d21f67ab505d0157d5aa73c579ba0c4737f1dab87dfa2%不明1
このグループの構成を比較する

エクスプローラーのエビデンス

FrontierCode

Sources differ; shown separately, never averaged。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1claude-opus-5-5_medium 2026-09-22config_90499d2a1f50ddc00ff8c1c68be58d73783300e7340eeedac5fe2d8cd4fd40ba55%不明1
2claude-fable-5_unknown 2026-06-09config_2687d157270f72d022ef9d602e76ea269ae5bbe66b7062f45d9519682576e6bc53%不明1
3claude-opus-5_max 2026-07-24config_01ae91077ba9150d840277a7e0fae15a73827719e0ba224bbba0bcd68fcff8fd53%不明1
4gpt-6-astra_max 2026-09-03config_3908ce8b0cfc8880b5377d99a32b9613c8f09ed7a7a7183bf560bcdd786ee0bb53%不明1
5claude-sonnet-5-5_xhigh 2026-09-28config_c8ee8e119935ab0d9704857eb2a639aeba26b58e63ddce2417cbdb43d8b826a552%不明1
6claude-fable-5-1_medium 2026-09-01config_766d77cd2cc468aa22a3b82b7ca4c80c53738534b6e94dc98a1bedc71520717b51%不明1
7gpt-6.1-sol_medium 2026-09-29config_813cd1d07d0def8f942f9d3a553db84f1e6cadceb3148bd682945d0778582d3450%不明1
8swe-2_max 2026-09-10config_fcf75fae7bddd18c493e261670a9e42da4ea61eb266e213af94cb0cc4eddf98850%不明1
9gpt-6-sol_max 2026-09-22config_6675e750a5409e535610dc739112c7e78133adcad0a05e81c34f3b8f68b8ed2a49%不明1
10grok-4.6_unknown 2026-08-12config_6f19456a4f118a4b3c66a978bb3ba438e8c520a2aab0e4b97f910bbeb57e5c3a48%不明1
11grok-4.7_unknown 2026-09-21config_7dcc189def701430024d662238b80569cc314c0b26ea0ab72260bea83bbff86048%不明1
12gemini-4-argon_medium 2026-09-30config_44949c993f4c3cd97c101e235417e3ff252439a7826ccff54b9f3f3749839d9548%不明1
13gpt-5.6-sol_unknown 2026-07-09config_17bd8197f3fd1a6dedb58a378cdf0895baf1b2a851d5854654a0c98850bba75347%不明1
14claude-opus-4-8_unknown 2026-05-28config_e749e354200461935a7ea9ae57b004b4e1f125109bb0bd8de48c32a13eebb61447%不明1
15claude-haiku-5-5_max 2026-10-07config_a68821c2c10661f545d7e609b739f19a781c52369b9eaba77eaccf147ff5c4fb46%不明1
16kimi-k3_unknown 2026-07-16config_5f807dbaeaa3f031f58ad044b8844ec9ef389ab36b3912602fc7d561ae9d853f44%不明1
17deepseek-v4.1-flash_high 2026-09-09config_61a32fe590eab15d5efcb1ba83333d817aee5d9fe0f91b42af1d47ac69312d9a44%不明1
18gemini-3.7-flash_unknown 2026-08-13config_979ea3f491ea0ce4d1592c2fd14fdd2c6614deca19982258189e852fab394a9844%不明1
19gpt-5.5_unknown 2026-04-23config_1e208f4033ab491d49ba0d4b503ba2fe32291e9d6098f5d4d8f8e49626881b9343%不明1
20claude-sonnet-5_unknown 2026-06-30config_418d28c0e375135ed44780ae367a2993f23a63fc87007d4b8db6dc526687251943%不明1
21grok-4.5_unknown 2026-07-08config_26c6959381309382a26d1cf08cc8cb0fe4f24b8d758ebb5d2c4ac13a6c1a98a442%不明1
22gpt-6-luna_max 2026-09-22config_5fc8d0b52c3b5a7b8683b5f976a6abbf7564672c93865747cd5919dfee8df55442%不明1
23swe-1.7 2026-07-08config_0af4579c0b86d218359bc028ab6200f92b82904f90d1f39e668ac8f04c0d71e642%不明1
24gpt-5.6-terra_unknown 2026-07-09config_46ae875a3954f9177367781981a840741d7fecb6bd533f37236eadb15d6e1e0a41%不明1
25gemini-3.8-flash_medium 2026-09-02config_94836814a3db1b798ae86f92e20e5703f30f8b4141bb65b1c40d102973dc9b0b41%不明1
26glm-5.3_max 2026-08-14config_e719512e6468a1452cb307be4752ef8a015ab1d5d3f3dcf6e1e101537c2eca9940%不明1
27gpt-5.6-luna_unknown 2026-07-09config_e9c34ce3587902bc4450dbe8a5810efe724222888ca3811c588b2672f99350f740%不明1
28mistral-large-4-0_high 2026-10-06config_dd8433e8032d4e3d4cbe931149d41351c90cf2bda2fcbf2efc093973f704718a39%不明1
29claude-opus-4-7_unknown 2026-04-16config_21128ad78dc713b9bd8c2c4e5785f2df83bd2f60bb7b528d3f0e729d08305bae39%不明1
30gemini-3.6-flash_unknown 2026-07-21config_ddc097c573d7683ddb36928a79826c1c7f1a5ca85c27242b5c4ab90445a76d9434%不明1
31glm-5.3-flash_max 2026-08-20config_4152f2f8d194fe4b83c3a222bedc39286e4dd8895b2ed2d4e8e99a4ce261c88e32%不明1
32kimi-k2.7-code 2026-06-12config_31ed039d75fd33b1057b150e5c418bd51423d38b8c7df9f78ce69ac1eb40d1dd30%不明1
33deepseek-v4-pro-0813_high 2026-08-13config_8a7e5239c8019349859cad629bfdf4bb15c9526124b744bcffc33b0132d38ce929%不明1
34gpt-5.4-mini-2026-03-17_unknownconfig_a1a7e4c8bd25d82dbdff30aac9a30694bcf9ddf729a11c7acbe2de38ab6b594b27%不明1
35claude-opus-4-6_unknown 2026-02-05config_e7abe35fbe8b8380a7ed4bd066f441d3c556b93518c20c7dee0040dc10f6c05727%不明1
36Composer 2.5 2026-05-18config_b97fd425f2526368e32ded2bdd621c90584703dd47438cbae1a93b378413ba2426%不明1
37glm-5.2_none 2026-06-16config_1cf4f3a461cabc583aa1fd99528a9a49cb7ad51c8bf54b17b41aa166067db96e25%不明1
38claude-sonnet-4-6_unknown 2026-02-17config_d16ff9a95d6839c1a8010ea4b24eaba8ce434289cba69a318f262bbddda8e0bb24%不明1
39deepseek-v4-flash-0731_unknown 2026-07-31config_1741249f61e43d5e0775aee38cdd65856748f0494f277058d9aade01fb20ef1219%不明1
40deepseek-v4-pro_none 2026-04-24config_0ec4386dd9cf763f25ad6463b4a4d9b24d51c2e322a61f5edc47e696326a88f118%不明1
41MiniMax-M3 2026-06-01config_fda1b5b794f636b1d632482936703d0882563edabfbdf6da15e1963b0c25d0fa15%不明1
42Inkling 2026-07-15config_2935bdf11dec76c7f9a65156ca62b11fc810ba21a9180eed041f73b855bc0ff714%不明1
43nemotron-3-ultra 2026-06-04config_ebc11e1c77c17935419f5c1b0f3e6353aca617bb1d1a067d09b9de75b28ed31414%不明1
44qwen3.7-plus 2026-06-02config_cfeeedc2c510d32d19e1045147c700762bec5ac62becc634ee0c0cbba69886c510%不明1
45swe-1.6 2026-04-07config_d2e00c33cb950bbd93c737b50cbdb921b656d56f3197311fd977d43ca75808649%不明1
46mistral-medium-2604 2026-04-28config_08f48de2f9787685aeb85fb80598d6df7be8e10ee16d859266f3dee6ead8064c8%不明1
このグループの構成を比較する

エクスプローラーのエビデンス

LiveBench agentic coding

Sources differ; shown separately, never averaged。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1deepseek-v4.1-flash-max livebench-agentic-coding:deepseek-v4.1-flash-maxconfig_a3f3f48128015b7048dc83697f2bfe8f012daa73f5ffa11178ec46caac6e0045100%不明1
2claude-opus-5-5-max-effort livebench-agentic-coding:claude-opus-5-5-max-effortconfig_623424b00ad7bf3ec909007676ec6f8473696f7c7356df518cb7c6a367bab58391%不明1
3claude-fable-5-1-max-effort livebench-agentic-coding:claude-fable-5-1-max-effortconfig_e61c4784e49f2ae6ebee18a6898684480b342962e8c12b229bbcdcb3ee90aa7481%不明1
4claude-opus-5-5-xhigh-effort livebench-agentic-coding:claude-opus-5-5-xhigh-effortconfig_44e877a45e05f65cfc614cff579a28937df62aeb0cce06842ef15f643a03f65180%不明1
5claude-opus-5-max-effort livebench-agentic-coding:claude-opus-5-max-effortconfig_fa03387b80782426a0083d86224b364186421f9f6475c7f7af53980146d2f4c479%不明1
6deepseek-v4-flash-vision-exp livebench-agentic-coding:deepseek-v4-flash-vision-expconfig_2f5283742b3da15d7054dd4c988df126247e4dd355031c2f5ce11bb9ef2217c379%不明1
7qwen3.8-max livebench-agentic-coding:qwen3.8-maxconfig_26d1a7c978290d54d7ef0eabebeaf9c0d1ce39c50082e92678df53715048bfbc79%不明1
8smaug-agentic livebench-agentic-coding:smaug-agenticconfig_67ad1d94b2e3e15e9350f6cbaeb2b779ea72938ddd0cfd5bbe55b326a9af397379%不明1
9muse-spark-1.3-xhigh livebench-agentic-coding:muse-spark-1.3-xhighconfig_27796316611daaff0f2c0d9c95585ae1251e0dc908250b7fa937ae1b56fd5b2a78%不明1
10muse-wonder-1.0-max livebench-agentic-coding:muse-wonder-1.0-maxconfig_d700d6c3add4e420345c60eb09730cc20a080f90620fb94130885fdc0ad67e6775%不明1
11kimi-k3 livebench-agentic-coding:kimi-k3config_3c44623be11a035903d5f110f1ef71d07c0e9527362cc1140d7af0b1aad175d074%不明1
12claude-fable-5-max-effort livebench-agentic-coding:claude-fable-5-max-effortconfig_dcebf770950f840525905cfd4cf209b75af292cc15028f199a71012506b8670b74%不明1
13qwen3.8-flash-next livebench-agentic-coding:qwen3.8-flash-nextconfig_4a92826c1f8edba2a821b99891d25bdc1177117a1e0ff6a16ac7b0250533115673%不明1
14qwen3.8-27b livebench-agentic-coding:qwen3.8-27bconfig_92f7a920aed94c8ff82916197320f4206f4e12206d8847aab897861be0e1e7aa73%不明1
15smaug-flash livebench-agentic-coding:smaug-flashconfig_7c7be6bb607f705ae5e1c71de96a36378ff23218a49b2a1bb8300ccc8e4a1b9572%不明1
16glm-5.3 livebench-agentic-coding:glm-5.3config_5012de9feced966a8ccc1480e05037cbe594c1bfa695e86c08bd7d3ecf4be8cb72%不明1
17smaug-mini livebench-agentic-coding:smaug-miniconfig_0ba097f94061fab8ecdb9f4f985ed096d19d6b4c3cad10094d01c3cf09bd81ca72%不明1
18claude-sonnet-5-xhigh-effort livebench-agentic-coding:claude-sonnet-5-xhigh-effortconfig_43a9cabf932f32a8fd6429e849f209b92fee99c00b1af2f130861fabf8759be470%不明1
19muse-spark-1.1-xhigh livebench-agentic-coding:muse-spark-1.1-xhighconfig_5bfd425c9188db5ba59751d48dc93c77f1f0e88472b5457fa33c17290bd9d6f668%不明1
20gemini-3.7-flash-high livebench-agentic-coding:gemini-3.7-flash-highconfig_fb0cc6574ed6ac7ffdf69a8b7c28eebaa2789283a43c989d28c70ed4f5d8ba3868%不明1
21muse-spark-1.2-xhigh livebench-agentic-coding:muse-spark-1.2-xhighconfig_9160731edb105c8a8b3bcd5cda3e79956fe3317b3523ed3d7757352ab9183cf466%不明1
22gpt-6-astra-max livebench-agentic-coding:gpt-6-astra-maxconfig_42a8b34ee9a4f138e063b1183909272846b4a1e63e5df2ce174ae8eea006b8c666%不明1
23mistral-large-4-high livebench-agentic-coding:mistral-large-4-highconfig_44e285c637d9552f68349686007879336b5415c6bda58f4101298f9621edd59c66%不明1
24claude-haiku-5-5-max-effort livebench-agentic-coding:claude-haiku-5-5-max-effortconfig_4a733a5bd5af122eb57fba1cb64e4885aeb57514c6f5df227e9e3113e9fbdd2566%不明1
25grok-4.6 livebench-agentic-coding:grok-4.6config_66e38e59192d3478e63c4c1b1a7f73ee6766beefaf61ff0a360b1f8e615d4aac66%不明1
26gpt-6.1-sol-xhigh livebench-agentic-coding:gpt-6.1-sol-xhighconfig_5f57290c240f2bc5bee9802b989fd3c1977026ea5cf1c2b3b90ce00de7c169b965%不明1
27glm-5.3-flash livebench-agentic-coding:glm-5.3-flashconfig_f2d90fa000d69788d8ba7c27f25f4a7c709b0392d758776a53c7b6fcafca4aa165%不明1
28grok-4.5 livebench-agentic-coding:grok-4.5config_e9fee7d161eab1a6a13dbba4437ec82529c71beffa6065c021e96213a7ce140265%不明1
29claude-sonnet-5-5-max-effort livebench-agentic-coding:claude-sonnet-5-5-max-effortconfig_c8a3216833070fac26546922f11e7510e41f719fb1159ebd788aabfb4de7d67f64%不明1
30gpt-5.6-sol-max livebench-agentic-coding:gpt-5.6-sol-maxconfig_f2b299001d72eaf68e7ae779b7f29eb19c55590f8023553b74abcc8f2bfff55664%不明1
31gpt-5.6-terra-max livebench-agentic-coding:gpt-5.6-terra-maxconfig_58e8d9d93f31d32dc713de617c9fabcce4f1c51501460215d332544ec8523c9d62%不明1
32deepseek-v4-pro-0813 livebench-agentic-coding:deepseek-v4-pro-0813config_b1ef602b63ec31a0274aea5b9c159ba86374059f9304b8eb427021c54b71febc62%不明1
33gpt-6.1-sol-max livebench-agentic-coding:gpt-6.1-sol-maxconfig_82e08e3f15c94e36919fd9156e552d54f5e51b402e0279d32ea3a46f06a063be61%不明1
34gemini-3.8-flash-high livebench-agentic-coding:gemini-3.8-flash-highconfig_5e651bc83d7908ab3a82f9c4e3abbfcb80c833bd97d5a51f6b15d46d7a3284d861%不明1
35grok-4.7-xhigh livebench-agentic-coding:grok-4.7-xhighconfig_dd6eb5fafb9fe66d1b28f8ca1764d18b2015f4c45cc5382013f88c19f54b777260%不明1
36gpt-5.5-xhigh livebench-agentic-coding:gpt-5.5-xhighconfig_f33b6bda00ff309df0ae96b94b139e89627e355cab0fda45ba69be2dea74444c60%不明1
37gpt-5.4-xhigh livebench-agentic-coding:gpt-5.4-xhighconfig_1cd35baf86058bbcb067d9230953ec4ea959b7fce959ffe1cb4caeefcb7259e260%不明1
38gpt-6-sol-max livebench-agentic-coding:gpt-6-sol-maxconfig_cff5173a77e25ec1878a770fdc5028856f9c8b5b2c1e73112740fb3c23a4b9e958%不明1
39ox-alpha-max livebench-agentic-coding:ox-alpha-maxconfig_32d6a5b3871bde90f48e9324210bdd27b7faa9cee90cf595e9e37c5ecc755eea58%不明1
40glm-5.2 livebench-agentic-coding:glm-5.2config_4263018f36603403a9ce293938692fe616138032641eac7fd56b42a11e988ed057%不明1
41claude-haiku-5-5-xhigh-effort livebench-agentic-coding:claude-haiku-5-5-xhigh-effortconfig_5951b361a7f236fd36757bbf3578a59742635d32b18aa25339eafe74293ae5e156%不明1
42gpt-6-luna-max livebench-agentic-coding:gpt-6-luna-maxconfig_b62038a08bf31d47cda50b8f9fa85bcef25deb9bc5e754a1a56da8c7f0ad8d0e56%不明1
43claude-opus-4-7-xhigh-effort livebench-agentic-coding:claude-opus-4-7-xhigh-effortconfig_c4ae48ff9433a87a1a6358ecb69351665798f780ba7ffdb21d03307cd0c9908455%不明1
44claude-opus-4-8-max-effort livebench-agentic-coding:claude-opus-4-8-max-effortconfig_ed201395926551ba01bdcbb0ab6747cb22040dc95c8d9c9a42e6695543f895c654%不明1
45gpt-5.2-2025-12-11-high livebench-agentic-coding:gpt-5.2-2025-12-11-highconfig_5da2e1e74c881e85fa6e95e1e86ff95f66d2b4db3bcb782d47569d8c2f86f18854%不明1
46inkling-xhigh livebench-agentic-coding:inkling-xhighconfig_210d4d63755602d853e3b391fcb8f9a03ae30508cd764711bf00d4f4d91478ba53%不明1
47gpt-5.2-codex livebench-agentic-coding:gpt-5.2-codexconfig_9361dcf948767508f060bd9b9435f00af0488858ffd4a34a05f051154714f14d53%不明1
48gemini-3.5-flash-high livebench-agentic-coding:gemini-3.5-flash-highconfig_519f10ce6dfa986f913e0a8b676529d9f942ca65529e5fc665ea999caf5d643d52%不明1
49claude-opus-4-6-thinking-auto-high-effort livebench-agentic-coding:claude-opus-4-6-thinking-auto-high-effortconfig_ded52f2edda6edd0f39efbf69e8c01653594e4a09fe06169692cc3171fbbfc7e52%不明1
50gpt-5.6-luna-max livebench-agentic-coding:gpt-5.6-luna-maxconfig_e3f67054973eae8d12055b2087d7828e8517edd8169c113ed014233ec9ab4cdc51%不明1
51kimi-k2.6-thinking livebench-agentic-coding:kimi-k2.6-thinkingconfig_f677d1d6c5a69e5214ea5163c28aef1da8b5a2adb2b6cc8b4add29a27be23c4448%不明1
52deepseek-v4-flash-0731 livebench-agentic-coding:deepseek-v4-flash-0731config_2056e61855394ea265f638b65933e2ddceee64a6bdae1084b01b7d1c98e9044048%不明1
53gpt-5.4-nano-xhigh livebench-agentic-coding:gpt-5.4-nano-xhighconfig_3e97d54bcf0ae865763a710c3fa4a4dc79fb5ebad56e761fcb2667d5f6d315b948%不明1
54grok-build-0.1 livebench-agentic-coding:grok-build-0.1config_17213fd3b89188a50a3c410f0cd97fe95586bdf87f092d2b406d2942d5c4562746%不明1
55kimi-k2.7-code livebench-agentic-coding:kimi-k2.7-codeconfig_0c53be86b5d3dd18a9cc284369998d3b5352e86cf821e466f2b774fa8dd53eb146%不明1
56gemini-3.5-flash-lite-high livebench-agentic-coding:gemini-3.5-flash-lite-highconfig_c13b9e922644048fd62e73f75e8cb23e5d51960a9e3e7e88e26f9ee985c95e0045%不明1
57gemini-3.1-pro-preview-high livebench-agentic-coding:gemini-3.1-pro-preview-highconfig_31ea798c91e15a1273c3aa128a89c3d99da42d7f87c53d5b092dd590d5d0e27244%不明1
58qwen3.7-max livebench-agentic-coding:qwen3.7-maxconfig_526c723601680bbd21f0d26b39723e28b38ed8ed5236854c5cdd8a7937214a0743%不明1
59gemini-3.6-flash-high livebench-agentic-coding:gemini-3.6-flash-highconfig_414ce51dc9cbb1149cfb361e38ceff9fff80dfeef3dd30a9bc476bf1daac4beb42%不明1
60claude-sonnet-4-6-thinking-auto-medium-effort livebench-agentic-coding:claude-sonnet-4-6-thinking-auto-medium-effortconfig_45f4a5f474ac65b466de3a1bb6e0574f3296076c1dec393c3e9968340b9274ed41%不明1
61deepseek-v4-pro livebench-agentic-coding:deepseek-v4-proconfig_69a8e6cf4d12564ee0b66d77c6bd5690116f378b1286c0e07b1956d455122b9241%不明1
62gpt-5.4-mini-xhigh livebench-agentic-coding:gpt-5.4-mini-xhighconfig_17d661fd889b3b6b7de1d2cf8f160a857b8f126cf7cb8b3cbd4ba6836a61b24139%不明1
63qwen3.6-plus livebench-agentic-coding:qwen3.6-plusconfig_a19b51c76a73ae2388dd7d025d3f04ece42cfbe48a8687b2b10e5ba04090d6b339%不明1
64minimax-m3 livebench-agentic-coding:minimax-m3config_70308968d63164d37ff3ab52d90f9b7371ff2e67a139e2831c42316b13a8f7ec38%不明1
65claude-opus-4-5-20251101-thinking-64k-high-effort livebench-agentic-coding:claude-opus-4-5-20251101-thinking-64k-high-effortconfig_90acaf2f301fca6bb200adc25a7bbc02f60b38f9fd69aeb3108a3efc4549a89636%不明1
66claude-sonnet-5-5-xhigh-effort livebench-agentic-coding:claude-sonnet-5-5-xhigh-effortconfig_e921269ddad45a601aeab57c06fe011fda91305085dfaecd382482a7e1abf63b35%不明1
67qwen3.6-27b livebench-agentic-coding:qwen3.6-27bconfig_a4613216c98e96a740df9aa99206df2177d766124e35a4ff8fc983fe8b33cef135%不明1
68nemotron-3-ultra-550b-a55b livebench-agentic-coding:nemotron-3-ultra-550b-a55bconfig_c4e39dd53ca9e460399d4e08d0be1f20632d8481fb1f0b1ce70267f9dcc29f2b34%不明1
69deepseek-v4-flash livebench-agentic-coding:deepseek-v4-flashconfig_cb8b3b1bc3c4d2cd9fd891b40959f91faca99d85fb611bf5efbff613f644da5433%不明1
70nemotron-3.5-lightning-30b-a3b livebench-agentic-coding:nemotron-3.5-lightning-30b-a3bconfig_b1b688f7f0f9bec6b0344ebf538a77007d9d3cb34df96b8ef759830f0858b3d72%不明1
71grok-4.3 livebench-agentic-coding:grok-4.3config_de3dfd64073bdada42dd848c34a68abad02091bfe4d48421a0ee5121140931ff0%不明1
このグループの構成を比較する

エクスプローラーのエビデンス

SWE-rebench

Sources differ; shown separately, never averaged。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1Fable 5 [high] swe-rebench:Fable 5 [high]__toolsconfig_4e7f75da05439b3642933e9e555d35f601be606b56be74f249c84b75c72c728565%不明1
2Grok 4.5 [high] swe-rebench:Grok 4.5 [high]__toolsconfig_4a0a36facd4c84472b72c62315364c005e7905eb5e714da1268a9e10704329fa64%不明1
3Opus 5 [high] swe-rebench:Opus 5 [high]__toolsconfig_e87585e983bf07a6c02dd9e122ee8c2ae6f5871b7d00cf81ae3e56adc6c7446663%不明1
4GLM-5.2 [high] swe-rebench:GLM-5.2 [high]__toolsconfig_31790c4ce133091479f0e475b3c27f17707bca63b16038b982c4a5d61978102263%不明1
5GPT-5.6 Sol [medium] swe-rebench:GPT-5.6 Sol [medium]__toolsconfig_fd0af5a9ef00c56831263638b341da9cf910d665474da73ea958d614ed9b297362%不明1
6Junie swe-rebench:Junie__toolsconfig_19dd924a998d790e3430cbf19f065f410d0becb402d0a54ff47187d54449d6a862%不明1
7Claude Code swe-rebench:Claude Code__toolsconfig_7097e56f2e9fd36c0bb8cfd5de2bdd1955c6c94706e13288dcf955eef65c38ff60%不明1
8Codex swe-rebench:Codex__toolsconfig_2503d09994edcf16bdf3fe21d749c4472d6a66f7df09489754741fad26b321f858%不明1
9Sonnet 5 [high] swe-rebench:Sonnet 5 [high]__toolsconfig_9f982bb8a565d848359fa715eb45b07fabf7e4f8ef2af465ef1db2647652406957%不明1
10Cursor swe-rebench:Cursor__toolsconfig_26a283926b59a657126e00e3aa5950ed50b55d8f192325c2a0bf6ac79ece30de52%不明1
11MiniMax M3 swe-rebench:MiniMax M3__toolsconfig_880d9ea0f0cb2554866d99d48bbc0369bee8d93f574e75e1e6d8c2980362d2a747%不明1
12MiMo V2.5 Pro swe-rebench:MiMo V2.5 Pro__toolsconfig_94baade9cb08003b0121bfcef2b4c713b9f593a25855407b4cf4cb6d84b30a2146%不明1
13GPT-5.6 Luna [medium] swe-rebench:GPT-5.6 Luna [medium]__toolsconfig_60a6476cf22eb1bb99856c673a62c0707918e28ff9c5fa48b7dd91c60084e48744%不明1
14DeepSeek-V4 Pro [high] swe-rebench:DeepSeek-V4 Pro [high]__toolsconfig_cd306ea55772d6cddc152bf079e0a2caf9ad5196e75005290fb2ccf87473564840%不明1
15Qwen3.6-27B swe-rebench:Qwen3.6-27B__toolsconfig_69ba7e04be3a3d97010f1c48f1491d2bee2976fa3ab917418a543bb819d4a19e31%不明1
16Qwen3.6-35B-A3B swe-rebench:Qwen3.6-35B-A3B__toolsconfig_030863e97e67f3c828545b380b319c8dc864d169055be74829235acb7d61e71b25%不明1
17Qwen3.5-35B-A3B swe-rebench:Qwen3.5-35B-A3B__toolsconfig_7e7a00e9aad734a48f0ad69fe3418df9a606e2eec0fe99859cf7a9fcc2c8c7ca17%不明1
このグループの構成を比較する

エクスプローラーのエビデンス

Terminal-Bench 4.0

Sources differ; shown separately, never averaged。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1anthropic/claude-opus-5-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-opus-5-5 | compute=maxconfig_a4d942a20322307fd6e9636c52a278ff4a5e01978199920fb00fb8816f804c0965%不明1
2anthropic/claude-sonnet-5-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-sonnet-5-5 | compute=maxconfig_67e5ebc1d687968374bab29dc9e8fff68eb4c19b68c1b8e52ba8b6789e3e8c9b64%不明1
3kimi/kimi-k3.1-pro terminal-bench-4-0-vals:mini-swe-agent:kimi/kimi-k3.1-pro | reasoning=maxconfig_63ac51751cd91ce5792f4d1edc31d988c09c854d46b918b313137116716799f364%不明1
4google/gemini-4-carbon terminal-bench-4-0-vals:mini-swe-agent:google/gemini-4-carbon | reasoning=highconfig_268c4fd7583fcf2a8819b2644ca19d2aea2dc4f9557f2a5e3aad28cc7ebcf89463%不明1
5openai/gpt-6-astra terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-6-astra | reasoning=maxconfig_f79848f58be493d8f8e4709588e507262f0e3cbefdb661d337bf1373f045142b60%不明1
6anthropic/claude-fable-5-1 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-fable-5-1 | compute=maxconfig_70fd062161f66f5b4f30232109f37776fada768e7df5c8040cd40fb835ac6b6658%不明1
7meta/muse-wonder-full terminal-bench-4-0-vals:mini-swe-agent:meta/muse-wonder-full | reasoning=maxconfig_8b32e0e69affa2f0d9c5f51a0a22c2b694e68b8e99f588bd7c1d2ee54869e1fe58%不明1
8google/gemini-4-argon terminal-bench-4-0-vals:mini-swe-agent:google/gemini-4-argon | reasoning=highconfig_044c4852af9099c15ca5f689b6d9ad5f4259b045aec5ffd09c1800952b6e0e6658%不明1
9openai/gpt-6.1-sol terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-6.1-sol | reasoning=maxconfig_12064d33c95534e5c1d654104d41c4dfffcc859a4d9052fd792ad3ce1d14f09555%不明1
10anthropic/claude-opus-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-opus-5 | compute=maxconfig_793b26ee00ea12db01dde2b1196d521312ed0e146ee113cbe03499105ced9ebd54%不明1
11meta/muse-wonder terminal-bench-4-0-vals:mini-swe-agent:meta/muse-wonder | reasoning=maxconfig_274928aff815ca51894a121ea18476136775e5e02c5bfdb373c1581503ca908849%不明1
12openai/gpt-6.1-terra terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-6.1-terra | reasoning=maxconfig_692136f5df9c1cfadae5e3ac8260d7a8f0a535844565e62350d882a30f57bb9049%不明1
13openai/gpt-6-sol terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-6-sol | reasoning=maxconfig_2d7b9977f8c32c3afca80d1b720a6e1945492ed3a18f0592b1b11010a187b50e44%不明1
14anthropic/claude-fable-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-fable-5 | compute=maxconfig_7dc104eca301135b012ba760830e438902861a1cac6d2dac22724402435adedf41%不明1
15zai/glm-5.3 terminal-bench-4-0-vals:mini-swe-agent:zai/glm-5.3 | reasoning=maxconfig_cddc94d2b46068e09a7674d95f5b9fc8fc0491ffc47e139dcc0ecf0239efd00a39%不明1
16alibaba/qwen3.8-max-internal terminal-bench-4-0-vals:mini-swe-agent:alibaba/qwen3.8-max-internal | defaultconfig_fb4ce6550582c053fba502e3aec8f2670f6ec0d4146e403bf60f964b2712aea939%不明1
17openai/gpt-5.6-sol terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-5.6-sol | reasoning=maxconfig_131c01233b3b53392683b38ed037fb1ab3e2c90c261611ff37b884a1e885431738%不明1
18zai/glm-5.3-flash terminal-bench-4-0-vals:mini-swe-agent:zai/glm-5.3-flash | reasoning=maxconfig_a599224774c5d9c06ce5be1d38a11951c8fa706858246c282c165857f55f864037%不明1
19anthropic/claude-haiku-5-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-haiku-5-5 | compute=maxconfig_af8d6fa7d9d8251fc685c69d08eb5db468361a2648a2356f91630c5b9e14ccd736%不明1
20alibaba/qwen3.8-max terminal-bench-4-0-vals:mini-swe-agent:alibaba/qwen3.8-max | defaultconfig_107aa87b7e3e502bb027533e0da53adae7fd523fe52cffb4a5347b0b0b2c013634%不明1
21deepseek/deepseek-v4.1-flash-1017 terminal-bench-4-0-vals:mini-swe-agent:deepseek/deepseek-v4.1-flash-1017 | reasoning=maxconfig_649bf97ab8c020a4f3df6f620223d339b93fe8536f556c7391789c7b0d142a3a32%不明1
22stepfun/step-5-preview terminal-bench-4-0-vals:mini-swe-agent:stepfun/step-5-preview | defaultconfig_68bb4abd87d02f5bb87664aaa77a46cffb65d2b439ed1fd7d06f6d88f62eadc132%不明1
23xiaomi/mimo-v2.6-pro terminal-bench-4-0-vals:mini-swe-agent:xiaomi/mimo-v2.6-pro | defaultconfig_ca491ab163b9cfa108adc4d8ca08662aafa05fc3feed7b2722e1da79a3e04d8731%不明1
24grok/grok-4.7 terminal-bench-4-0-vals:mini-swe-agent:grok/grok-4.7 | reasoning=xhighconfig_b5a359bdb1c5d9974006aaba83e17f1ef16e06f1e54efca9459570289547d98629%不明1
25mistralai/mistral-large-4 terminal-bench-4-0-vals:mini-swe-agent:mistralai/mistral-large-4 | reasoning=highconfig_7d3e700b8eb9e23b31b1870e0208fc28e0f5a65e0a41d419f8bbab53da61dacb28%不明1
26mistralai/mistral-large-4-oss terminal-bench-4-0-vals:mini-swe-agent:mistralai/mistral-large-4-oss | reasoning=highconfig_5342124e4f976e6be30cb4b45b3d6987af20de44806039e4ba66f47b0e4a7e2526%不明1
27minimax/MiniMax-M3.1-flash terminal-bench-4-0-vals:mini-swe-agent:minimax/MiniMax-M3.1-flash | compute=maxconfig_9d70d49242808041792d2e801879a45a8b0801770b00c5d5daf02919b58a1b8d25%不明1
28meta/muse_spark_1_3_max terminal-bench-4-0-vals:mini-swe-agent:meta/muse_spark_1_3_max | reasoning=maxconfig_748cc55b672a417aecd3d47b9db51fdfda3a75f3db510c37527ce09db37ade3a25%不明1
29xiaomi/mimo-v2.6-flash terminal-bench-4-0-vals:mini-swe-agent:xiaomi/mimo-v2.6-flash | defaultconfig_468f064cb6fb74ed44089d478e0db5963c094da6b81bc7580b0ec1e20442165524%不明1
30anthropic/claude-opus-4-8 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-opus-4-8 | compute=maxconfig_93667b6f291e652be1ca88b6cd62c4c4a6f0ed4b0295c0622bbc45eb726bc12d23%不明1
31openai/gpt-5.6-terra terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-5.6-terra | reasoning=maxconfig_a9209d2817fe7bdcf512119e986a3099937d5c4869df005775198932c06736a423%不明1
32fireworks/ember-1 terminal-bench-4-0-vals:mini-swe-agent:fireworks/ember-1 | defaultconfig_37d8743caa2c7f6f7e1a50e6cc87a141c33ce567bf6248ea8338413c72722aa821%不明1
33google/gemini-3.8-flash terminal-bench-4-0-vals:mini-swe-agent:google/gemini-3.8-flash | reasoning=highconfig_94707b665c998a1b2975a555c219930198151633acdf118d8a47437e75fe535120%不明1
34deepseek/deepseek-v4.1-flash terminal-bench-4-0-vals:mini-swe-agent:deepseek/deepseek-v4.1-flash | reasoning=highconfig_c1324e863c16572a096396f84331c0431f39fdd8e7b45e69868defffb20e4eb220%不明1
35deepseek/deepseek-v4-flash-0731 terminal-bench-4-0-vals:mini-swe-agent:deepseek/deepseek-v4-flash-0731 | reasoning=highconfig_bb1783ee5a862473eb09aa19e22767801e869fe9ba98af9bb3fdf91fa2c1c58d19%不明1
36grok/grok-4.6 terminal-bench-4-0-vals:mini-swe-agent:grok/grok-4.6 | reasoning=highconfig_3d11f3dec5680ff0e8ad11dc54d38b2d5e5524177534d607604ed408c3408e3d17%不明1
37kimi/kimi-k3 terminal-bench-4-0-vals:mini-swe-agent:kimi/kimi-k3 | reasoning=maxconfig_6aff70367861eb41533b1229a54beefe27cae62ae136b8c9f78a681b70a8bcd017%不明1
38deepseek/deepseek-v4-pro-0813 terminal-bench-4-0-vals:mini-swe-agent:deepseek/deepseek-v4-pro-0813 | reasoning=maxconfig_649d2384e923d46f83885f2afbc377e8fb75173a9e277ca201927973d98bb3ed14%不明1
39openai/gpt-6-luna terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-6-luna | reasoning=maxconfig_bb74f34b9725ab1ece6e09568f342257e355b77fea96184c78491a9db055814a14%不明1
40google/gemini-3.7-flash terminal-bench-4-0-vals:mini-swe-agent:google/gemini-3.7-flash | reasoning=highconfig_70e133a4696b602f43cc417565bd12515b3724fe84c2143258319c79f815f23612%不明1
41openai/gpt-5.6-luna terminal-bench-4-0-vals:mini-swe-agent:openai/gpt-5.6-luna | reasoning=maxconfig_6d5043275fd9ea24bd539a728bd298339578d5465900f3ac1238c3e5784ae56b12%不明1
42deepseek/deepseek-v4-pro terminal-bench-4-0-vals:mini-swe-agent:deepseek/deepseek-v4-pro | reasoning=maxconfig_6065e3adb55e1fd19b219495b960f3ba2a9b2cb166f7eb0ae0985cbf9ef26a2511%不明1
43anthropic/claude-sonnet-5 terminal-bench-4-0-vals:mini-swe-agent:anthropic/claude-sonnet-5 | compute=maxconfig_55199371d8c415af13d28469d11bb560f80c07536b968810a11cf7b3f301e3d211%不明1
44meta/muse_spark_1_3 terminal-bench-4-0-vals:mini-swe-agent:meta/muse_spark_1_3 | reasoning=xhighconfig_741e18ea2a9ea475595736f0251fe731573e0fa51908bd31061f93fa7c16075311%不明1
このグループの構成を比較する
上位セットを定めるための独立したエビデンスが不足しています。
  • キャリブレーションが検証されていません。
  • 構成の重複が基準値を下回っています。
  • 独立したベンチマークファミリーのカバレッジが基準値を下回っています。

モデル構成 · 直接プロンプト

Exploratory - not a ranked winner yet
rg-coding-general-model-configuration-direct-prompt-model-configuration-v1

エクスプローラーのエビデンス

SciCode

単一の出典。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1claude-opus-5-5_max 2026-09-22config_58b43df56ccdb3b49c290ea5a3f5bd304edde074bd05a97e4267a309a93d13e767%不明1
2claude-opus-5-5_xhigh 2026-09-22config_fed93fc128e73cfa299ef9faa5ea0c9d7412ce600e47588325846e1e46ca16b265%不明1
3gemini-4-carbon_high 2026-10-28config_bb5251f498efd88d100369ec4c0b3dc4461e6e0ae9ec161a5221367ccc0d71e764%不明1
4claude-fable-5-1_max 2026-09-01config_0fb3f03e52dd04e1e410fcb6fcbf3895aa0c0e4c2a75830e44bbc9a24a60a0a363%不明1
5gemini-4-argon_high 2026-09-30config_207f9c411d59bcde3bf970e7af83b7b5f6288b7dfbdef7e1a2ad4ee5dfb97f6d62%不明1
6claude-fable-5_max 2026-06-09config_8d34c7dd565f0a64b9d80273b41cbbdfa54d2e2a9f8e5b9fc3802846f3aa05c461%不明1
7claude-sonnet-5-5_max 2026-09-28config_9499c796f8ceb4ebf985bc887d35fb22dc78ba4d9a16755163b719f5f7f14df161%不明1
8mimo-v2.6-pro 2026-09-21config_2054231b5b558c35832f9e1c97ef252e65b94c160d010cf32625f3ae3b697e0061%不明1
9claude-fable-5-1_xhigh 2026-09-01config_d48a892c08a1da22463a0547f533e77e0097c98af2ee315884384c432ba7bedb61%不明1
10kimi-k3.1-pro_unknown 2026-10-23config_43da3ed478dd5d438ee5c9247d39b75d75b6914dc612747a0d7aa2070a5ffa8b61%不明1
11claude-opus-5-5_high 2026-09-22config_5e2eeaba85ad807c94176165ba344bfe287e8963cb59e6470a58cbcdb6b8480960%不明1
12muse-wonder-1.0_max 2026-10-12config_0da0a9414492e7b8092eef021a4da80d6d52c5c43c3b5d69c8d837d10b9cf6cf60%不明1
13gemini-3.7-flash_medium 2026-08-13config_f23a2989c021a0521977017290b5fc5dadc083222007c07593dff7d1b7c0c21d60%不明1
14muse-spark-1.3_xhigh 2026-09-02config_1501233e0a353907564f0b0065bffa7d95613131903c948c969957dd8cf05f5060%不明1
15kimi-k3_max 2026-07-16config_d707a33ef8e8b94ed2cdf47b839b4e654183a727a95543e4e877618d832b211259%不明1
16claude-opus-5-5_medium 2026-09-22config_712615b07be9e67bd8bdc35448a271c534199a766fd31bc41dd5517af4f528dd59%不明1
17glm-5.3_max 2026-08-14config_9b0205d7ef18d1ac04522fff944fe42e2b0b2d72f282ffbbecff5ac70877e58559%不明1
18step-5-preview_unknown 2026-09-18config_bdf4856c7934b836ce742a9b876094f7a53a68aabb69d91e776432c75f0b52b859%不明1
19muse-spark-1.1_xhigh 2026-07-09config_01ffd2400828a6f67637d09c850fc15b0d6e2251d5bf0568eb9e02206abbec2a59%不明1
20muse-spark-1.3_max 2026-09-02config_201318b66046774023ebae7370d1d01bd091224d339f0662bb73ebfe75e902e659%不明1
21muse-spark-1.1 2026-07-09config_6680c7d899264ddc8f1d2f7d9f6853c6228654243b1a5537a6bb29a4ef3cc99e59%不明1
22claude-fable-5-1_high 2026-09-01config_16f71696764f52d525181a95ab21c6bd069be3307e1e86f976f79961cee4eae159%不明1
23gemini-3.1-pro-preview 2026-02-19config_76cb6b8fc4da622a11f59e9b038fb836eaadd1f9bffb7e86002237b552cc984359%不明1
24kimi-k3_unknown 2026-07-16config_c9aa04521808d1807739cae4874472c3e1b7bf1138f50ef1fd7b2827e58e79ae59%不明1
25claude-opus-5-5_low 2026-09-22config_c888e4c56160f0efc3bdef650c2acb0c40b23a35321bf89972c8276dd691d51759%不明1
26Muse-Spark-Open-816B-A42B_xhigh 2026-10-15config_61677af594f9b7895cb17cc9c8983532b2b632468ab7d72c682a790917e3168358%不明1
27gpt-5.6-sol_high 2026-07-09config_09dd4673bc766c763c65d49d602d243472ca2f09b3aaf81a1d208d39495fbcf858%不明1
28grok-4.7_high 2026-09-21config_59dc2870d2bf7381d4a12e03744ce477788ae035bba67cf1d0fdf5cd443929af58%不明1
29gpt-6-sol_max 2026-09-22config_a89bd445f30b3c6ba0948fca959b7de745da7aba56fa547de9f703d6f06b833958%不明1
30gpt-5.6-sol_medium 2026-07-09config_26692174c93318a353e8f900a3d0718cf761a0f3b2b1cd5d16ffa8205e82239557%不明1
31muse-spark-1.2_xhigh 2026-08-05config_5e6983c6eeeefacddc058f3b40dc969f6fd2179e8b4ba0fec62bd042940b7d1e57%不明1
32grok-4.7_xhigh 2026-09-21config_aff501d3317f1cea99c1ceead9d3731a1c90bbfbbb4912d7a6dae65976efe0e957%不明1
33claude-sonnet-5-5_xhigh 2026-09-28config_5313a04a6568a5ad96dfb3a876cc988fd59e08ca49087e4a745039af299b1ef857%不明1
34gemini-3.7-flash_high 2026-08-13config_33f22ae7a384cd21402e26fda58a9e657505aa8cadbbc9e8067f860321792f8e57%不明1
35gpt-5.6-sol_xhigh 2026-07-09config_365e1900c8389cbd6cce2bb203de7828bcb4a6566159dface9865435032a800b57%不明1
36gpt-5.6-sol_max 2026-07-09config_754c0ab021ba6f8a46654f4bb97ea19533aabab5920731757714e1b600fb019c57%不明1
37claude-fable-5-1_low 2026-09-01config_95bffa1f536e6ca0f278ba25fb4b1ce84af1963f2a3de4d6e85e5b28d6b1916557%不明1
38gemini-3.8-flash_high 2026-09-02config_4a24b550a22ac751cf70dc309ba28e0a8637c5d06c7c7ec8ed3209b6d5d425d757%不明1
39gpt-5.4-2026-03-05_xhighconfig_669ac29314d587df9c29b141b60d7f18b676f6c745cdec1c00fbdf054590d74257%不明1
40gpt-6-astra_max 2026-09-03config_459ac8dc316851dc4e50c105aee8cd97974594979a58b278e5fc558abc01696a56%不明1
41grok-4.6_high 2026-08-12config_740edaa78ca55598fe4da4f3ec13156ec451e623fe87cd1c0001b17f4eb7830c56%不明1
42claude-fable-5-1_medium 2026-09-01config_57d65ffcb87aaa05af656e2575faae67b683730335706b1990e4b24a98d17a4356%不明1
43gpt-5.6-sol_low 2026-07-09config_a144462859844e2b3836fc10c764249d8f7beacdeea07e54303302202497d4cd56%不明1
44claude-opus-5_max 2026-07-24config_d37ed7f2218f8db72bc665b7698b73d353a4c7b7f2f08e1fb26a6c337af15f1c56%不明1
45gpt-5.5_high 2026-04-23config_e5a59f69c290299c8fcec0331e4ddc88025c9d1e8c6bba4df7654586fdeb308d56%不明1
46deepseek-v4.1-flash-1017_max 2026-10-17config_86346a8a147355127f95ad4747427307541030b80b423cf4798676323e5fe55456%不明1
47grok-4.6_medium 2026-08-12config_9fac37c35da2df6f815eb842df6451185c8264b25a3d38e375c62efae452cad656%不明1
48gpt-6.1-sol_high 2026-09-29config_1f8bb9cdde7bb4d960d11b71b5397d70d937ce9543309f6194a6d5537b70b0ac56%不明1
49gpt-5.5_xhigh 2026-04-23config_f41f84a695256fa2b7da8a9708d085bd63c9e933a320182dbae6416cd6c2a50856%不明1
50gpt-6-astra_xhigh 2026-09-03config_94465539e3d47df6f6c3c832d881ff8ed9b5b6abd13cb9691430a68f11efedea56%不明1
51gpt-6.1-sol_xhigh 2026-09-29config_fa454b7cb5bb76cc0b0c3476496e4354263f80bd47a666dc0d78514ea8f6480756%不明1
52gpt-6-astra_high 2026-09-03config_4a61134a89c8c322be80e423e6dad2ee46a2757c726c4d035f9985eb2118797c55%不明1
53gpt-6.1-terra_max 2026-10-26config_2f092ce13d02aad6944b9789eada627e1a216778e2b83f590148e9a08fdbdfa255%不明1
54gpt-6-sol_xhigh 2026-09-22config_97904dd97582cb55c03ff438ae1e44c03421a1c4f2b4770010962a2116891df355%不明1
55gemini-3.8-flash_medium 2026-09-02config_c95b66bb9fb419e08316645d00bcdd46e7ba251a460914264205200ae50d153c55%不明1
56claude-opus-5_xhigh 2026-07-24config_312386a3a2ba3625b9836322e87ace7d81d1f6e72e39756cb61b78b92c57360a55%不明1
57grok-4.5_high 2026-07-08config_6627d3698d23a77db1377ba90223df3c8b40d39fef1961f8a668172f3084650355%不明1
58gemini-3.8-flash_low 2026-09-02config_9c599ae78680ea6d6aaa202c417f2ad8917745bff422f21c4a38932377425a4555%不明1
59claude-haiku-5-5_max 2026-10-07config_be86aff981c838ad0f856c4bc46d4f4b4f4aa29fc55357326b66e9a3bde0cf0f55%不明1
60gpt-5.6-terra_max 2026-07-09config_ee67687c955bc9f26fc4db66d5f2cc4b55b08ccc28ec113eed5e34df38deb85c55%不明1
61grok-4.7_low 2026-09-21config_89e24dadedd1547e720a7187ef1f0fafe6f9921cee884413f90ebbe75b7743a355%不明1
62gpt-6-sol_high 2026-09-22config_cede3be5deb4df7e753b7817ad55218130ad31c0896193f50159949bb6c366a755%不明1
63gpt-6-luna_max 2026-09-22config_094f403a72365841df9ab1f46c22fa61ac61c04909e6b2e2f0ec085342959df455%不明1
64claude-opus-4-7_max 2026-04-16config_762f169f1a30ab912f52f0d6c4ff6e3bfab1e423fb035deee5c85a4291f012fe55%不明1
65gpt-5.5_medium 2026-04-23config_af6b5690f3be09f0c3060a270b1749f2a1e54019ada6c5e7ce17dd889a76061555%不明1
66claude-sonnet-5_high 2026-06-30config_d7d03c544d0089d87a8cb982edd31216ad956b0ec19ddca334bd8df82882e6d054%不明1
67claude-opus-5_high 2026-07-24config_e9999c2aeeab0e14fcf36e83362dfeaf1edd3fec4048f59500790d96b703dc6654%不明1
68gpt-6-astra_medium 2026-09-03config_4b222f5741b250aed06a506403d08dd0234e0cd90b24a24f9a33b8fafe0a33b954%不明1
69mistral-large-4-0_unknown 2026-10-06config_afb58c266c8a981d7ebeebc68802bea97c266dc891dd28016b34350e00d879b954%不明1
70gpt-6.1-sol_max 2026-09-29config_b43cfb6409de530a548099d6e799fa06d4e40cc964681a2a293cabdb9984797654%不明1
71gpt-6-astra_low 2026-09-03config_2730aa242fabab2a424069b63462fdbc8362e5ba5ceec28bd9cc4057422ee7ba54%不明1
72claude-sonnet-5_xhigh 2026-06-30config_e5f43ffba18766872794753a2ee0324bb5a032dc17ba7878c2831a9e888a7cdf54%不明1
73gemini-3.5-flash_high 2026-05-19config_390526fd99a083b7192062a0cd537e06256b47ee7d3069129f616628b7cf8bde54%不明1
74gpt-6-sol_medium 2026-09-22config_7b8e8339811e7cf29e87ab4a75379ae6b6acc970f2154f720cf53b3f76854dba54%不明1
75claude-sonnet-5-5_high 2026-09-28config_ec927bd545df7f883f6213045b4ccc2a8510248b0fe6418985bc28573d51bf3354%不明1
76claude-sonnet-5_max 2026-06-30config_a7307c6e09f25db9ed990b968b511109dfa6c72816ae60d119dc20d2da0030f254%不明1
77gemini-3.7-flash_low 2026-08-13config_d3c884e85f28bda9e9edd3e8e47ed833e033b90c23589e4d55aa4f69527b52c754%不明1
78gpt-5.6-luna_max 2026-07-09config_e587502fdc3b99d900e303059a9701e54e761d87c3795cff54c722c68dfa0a9054%不明1
79kimi-k2.6 2026-04-20config_79715e092ebd32adbe6a8ef5b8a297d057b1344f6dab572c9d7bc5aceab3e4ad53%不明1
80gpt-6-astra_none 2026-09-03config_9a499acab7ca7e601e1b9875cd1f22632cbad995914292c292dfae2f0b7fa1be53%不明1
81claude-opus-4-8_max 2026-05-28config_c314fa4ba0dc0d51e164bc7dd183557311e01b2847a04dd5c261591fc008f79553%不明1
82gpt-6.1-terra_xhigh 2026-10-26config_1971b5caa4aed5c560de854778d2943c8f516e68f1b485727c5670aaba1dbd0853%不明1
83gemini-3.6-flash_high 2026-07-21config_db4a45c2def6fe6e591043d15ed89e65b5205501b8aae28cba7a0e5283b3797753%不明1
84gpt-6.1-sol_low 2026-09-29config_59e6c749960e77b2a68d75c49415031c7264cf9ea310a6040dadfa232ab0a25f53%不明1
85gpt-6.1-sol_medium 2026-09-29config_df4e2cbccd682a1407151d157cf96fb8759feba2f0a5cc7c3c4b2e0b7e690b2153%不明1
86grok-4.6_xhigh 2026-08-12config_423066acf3db4bcc8a6899c13c716816cbd45ca5ca0d0812d6fd4eb796a3e6dc53%不明1
87claude-sonnet-5-5_medium 2026-09-28config_598b1a3e088048d6124ffffd85e8dbc9e5a4b5a11c52cb76e1c86b61aeea187553%不明1
88kimi-k3_low 2026-07-16config_6958f9c23200d1d6d10fbac93b3c78d531c6ec598604eb85f1ec2d293445ff0153%不明1
89gpt-5.5-instant 2026-05-05config_b8dee1aa7b5f25e8f711bb4620aec7e478ad12818b8c3b266a6bd88950a4d83653%不明1
90gpt-5.6-terra_high 2026-07-09config_169ff121b1a860195c4831f3262a2fc8051385bae12512ec3561690f6ea9533452%不明1
91gpt-6.1-terra_low 2026-10-26config_175547a43477669dec8d58617cd12902cc6b6d4068863cc09bf26abc7a472b9952%不明1
92gpt-5.6-terra_xhigh 2026-07-09config_0553f1ce3f65c765004713d72ec9a6749cede42dd62add7b60d8d294789a463e52%不明1
93gpt-5.4-mini-2026-03-17_xhighconfig_c9a997e218e4a0896c7877fa40c69a19f621c3536c71c67f324ec6e7bf1a297052%不明1
94qwen3.8-max-0902_unknown 2026-09-01config_f24232a8fe917b99a69105d2bcf33e5aaaa17945c17c7893d9df8cfdd0b9571652%不明1
95deepseek-v4.1-flash_max 2026-09-09config_f17a690b7481f04ee8090baa9c7e44dd2c5b5ec66d05fccabdd2eb59f76ad84652%不明1
96gpt-6-luna_xhigh 2026-09-22config_7ed9e7be4756fb88712d40a6f699e882fe9d50f8839c27247a54e27af37643f552%不明1
97claude-haiku-5-5_xhigh 2026-10-07config_f7f699d0f8036b7b43f11cc5341903f3314f1996a4d3c70f7c8ec1f6f5cae88752%不明1
98gpt-6.1-terra_medium 2026-10-26config_10c637f4cd6c84b0e18f3cb20cb9576974c4937a53a1dfa3ce438a179e355ff052%不明1
99claude-sonnet-5_medium 2026-06-30config_1ce6e62878686fa47d11e1c40a92f89967a4beeebeef2bdd7a0b9c03e19657d352%不明1
100gpt-5.6-luna_high 2026-07-09config_6028644d4e821f0579c6cbc821b016bc174f1f7894f663314e8af46a81ff60f152%不明1
101glm-5.3-flash_unknown 2026-08-20config_e003e0735fde66a46917c4621169336ea3e092c4cbbc1729191e940448fe242d52%不明1
102gpt-5.5_low 2026-04-23config_ec648392146d2532f4be837e945ad5a55f79b5a7208f1c8e3c5068f4503d69db52%不明1
103gpt-6.1-terra_high 2026-10-26config_f581c18137cad12063ae48f87789a62aee6f3dcc09f195f533902de0d470820752%不明1
104muse-spark 2026-04-08config_d44b10f0e691c37e7c14b057261d6a0b88129cab973e5a6904128f219f34f30e52%不明1
105mimo-v2.6-flash 2026-09-21config_899ccc4dce494b0cc3d1964575590c13308ffc8f7085865ed111c7b3cad7bace51%不明1
106glm-5.2_max 2026-06-16config_d0c334f96578baf589fb8ef931575652526fe6c2aee1744434dcec5b3b33776151%不明1
107deepseek-v4-pro-0813_max 2026-08-13config_b62b7a05e1a62d6b54026f563dceefeb675c991c86b329d264b1fe65d16c4c1f51%不明1
108gpt-6-luna_medium 2026-09-22config_287bd865fe379818fbb256e3a010d2e31fde1366ec4f27f72824561ef4c85ef951%不明1
109claude-opus-5_medium 2026-07-24config_6a7ee5b9215fb4c23727c8a8c3fc01013e9803f28750d5fe66268220e053baa851%不明1
110gpt-5.6-terra_medium 2026-07-09config_0d4e5a2402aaff31642ebd7721b23cab7eb8b1609c31e74acac46dfba223c11850%不明1
111gpt-5.6-luna_xhigh 2026-07-09config_ecfc0e401e83337db1bb0c65cd1fcaaecca815a34a2da103c128cf312d8404af50%不明1
112gpt-6-luna_high 2026-09-22config_572094e4a437a964e8cdd9baf543b8707332e7d40676f47168607b00c4b8c78050%不明1
113gpt-6-sol_low 2026-09-22config_07edbaa3e394c3fb46319648c01a6548fd7329cbef16deff411a83e81966b3ac50%不明1
114grok-build-0.1 2026-05-29config_22a107e3f9a2a93b4e0466b2196fdaeb6eb7e2fe864e7df301c890432f13388450%不明1
115mimo-v2.5-pro release-date-unknownconfig_5aa91367a1a7b6524aa888f2a77ede1c57279a85a010fe2f73a13968f68df68d50%不明1
116MiniMax-M2.7 2026-03-18config_05fa227f49ebb1dccf5e37d0409c290368b83cb9423fe7dd4bdf6e5cde679f0850%不明1
117claude-sonnet-5_low 2026-06-30config_6723ad02d0ab7aaee0252b65afb623a184c6cb543fcfd715491e066f29e08fdd50%不明1
118deepseek-v4-pro_max 2026-04-24config_81a148910f4f5d063c4777c130c3a1c7ec9c31ee69404157936c264a9955c69e50%不明1
119gpt-5.6-terra_low 2026-07-09config_1ca335de2c353f962770d692fbdbde405136c4651fc7ffb237e919fdf5e16f7450%不明1
120deepseek-v4-flash-0731_max 2026-07-31config_76e966a5ae67c85215c7c7be133d724a9883d671e92adae32024d7fbcf74946250%不明1
121inkling-small 2026-07-15config_58bd495dff29b35aab1d3c2e11ea2c2b58afae23c787418eeeac36880376d4ae50%不明1
122qwen3.7-max 2026-05-19config_b640a0f0f574deb0fe63a981004ecf305a377bedb269ae6fc804b2bbd575f11c50%不明1
123grok-4.6_low 2026-08-12config_abfa7afa2b24605e220da4c04163a9159ff9d55db5a093c00026959a676ee88449%不明1
124claude-haiku-5-5_low 2026-10-07config_6683f2646ba6f03e4e9a39b1517cf4731f80cf6b86042c4936fd0afe0a28bb7349%不明1
125claude-sonnet-5-5_low 2026-09-28config_26b14ae280fba0169f4935fa782a2e99ab169c79e2e947edc49d60c9c68fe05349%不明1
126kimi-k2.5 2026-01-27config_20bd261d79345ca93b7e9f8fbffbe3ffb337c6bbc53984181992ebbf13c7bfa249%不明1
127claude-haiku-5-5_medium 2026-10-07config_922cbd0c002847f047e02f49ddad5d92694375fec788fbcfe97687c29140477249%不明1
128claude-haiku-5-5_high 2026-10-07config_eee4da09dbac8555553bc292fe1030f06ce59b5d700fe80048eea68b4dc2aae649%不明1
129claude-sonnet-5_high 2026-06-30config_23988381db43c57d763714bc3afbc1146f6ebd7bd60ad3f3918eff30e2ea45ac49%不明1
130grok-4.3_high 2026-04-17config_da0ff4c210aebd03e7fed43783e5dc24591f862e2326f741664d346534594f2848%不明1
131claude-opus-5_low 2026-07-24config_2c9a5523fed36b3b8deec3235a526f7cb7a36e630ca79a86dfd92ce8ed94c30848%不明1
132kimi-k2.7-code 2026-06-12config_60744ea1e7a29d77cbabcb1a95f52e174f0d596baf5b52657391d809e36c4e6948%不明1
133gpt-6.1-terra_none 2026-10-26config_87ef2d889fc4f72d234b682dd95851b7082bb4840e3d42c4cf08bb6acbf9c50548%不明1
134gpt-5.5_none 2026-04-23config_437fe38e94e8949f6b6881553245e45e95dc59f5c9f5a7f2b46863bf226428d747%不明1
135gpt-6-sol_none 2026-09-22config_7c25f3bc88ee60db87d31f80ce3fdc6d557cd98f00d76766273a4a0c5794c30147%不明1
136gpt-5.4-nano-2026-03-17_xhighconfig_74bba1ad86fc3500414a4ac62b1c76f613b2d13176bef626a8f6423cac8f1da347%不明1
137gpt-5.6-sol_none 2026-07-09config_27d8490506ac6353a26b3829dfe8d385c7e65ff0402e082002ed6f3f2569e44847%不明1
138MiniMax-M3 2026-06-01config_3e0345326dec03865c1da9b9ff9ae505682cdfce8ebcac223715115d75e1bb2f47%不明1
139Inkling_xhigh 2026-07-15config_9fd67b519c3db8747c690a2bee13d76784db1734e4c8550225034ad9891e639747%不明1
140gpt-6-luna_low 2026-09-22config_dd54c70b7aee8c8d54cd45377c8d963079eb38f90cdcbde58dd49822cf42a86c47%不明1
141gpt-5.6-luna_medium 2026-07-09config_23b1b1ada3c318e22831143fced18c5f9115955751b3090d82103681b08b886247%不明1
142claude-sonnet-4-6_max 2026-02-17config_d0372d242a2ba1e1b4e220a76be2b1396abc61a2d94cf69497d19520b1bb6a9547%不明1
143qwen3.8-27b_xhigh 2026-08-14config_218d071d3c21c8ceadca832421175f4cc1a2748ebccd2a7a1885c5cc12d51a1047%不明1
144deepseek-v4-pro_high 2026-04-24config_4711a6c093dc5b8fb240f9f079eb13e040171a66491b39e8479c46d42f16c28046%不明1
145gemini-2.5-pro 2025-06-17config_dec9e48828317d5256e58ace29fed0ecfaf24436f73789208651a601d05a99c646%不明1
146qwen3.7-plus 2026-06-02config_d901dbedd55623d8973f4873c3b1b477369eb1394f02ade85b320ce2e9e9bc9846%不明1
147gpt-5.6-luna_low 2026-07-09config_e6ac58dadc7a9a4b0e1e46d1b8971b6a6d9281bfda7e67ff0bd38f457794daeb46%不明1
148claude-sonnet-4-5-20250929_unknown 2025-09-29config_8a04dd7a8a2743318e8e500db970d741f511352ae3a1d5c202337bf9199b273a46%不明1
149gemma-4-31b-it 2026-04-02config_5d4ed362cd6b97e04954292d38c11698bdeee4f2da90f07076cf41141dcaf05f45%不明1
150gpt-5.6-terra_none 2026-07-09config_9611de6513af4a2099149e6652d41274a05bc624c94f0daa1fc7df1c94f066e045%不明1
151glm-4.7 2025-12-22config_e90fe935b7223033014e06472037aac522adeb8392728db7ac0492c29e40352845%不明1
152Ring-2.6-1T 2026-05-14config_88561a1e72f466768164d0f4d1875455f40f137ac0478f166ce84d655223345545%不明1
153deepseek-v4-flash_max 2026-04-24config_5c6c3baca5ad00d855c323b236f792df125149dfabe3e5c86587c0625ce30cde45%不明1
154muse-glimmer_high 2026-08-10config_66e5d8cad6b60abc0acadb3b9cf18e472ab0fedc65ff3bded3cb62c1d8ee344345%不明1
155glm-5.1 2026-04-07config_e2805e433c7480c6933d82a7c7df43d82c39a8ab24bbabca1373901f98c3e1c845%不明1
156gemini-3.1-flash-lite 2026-03-03config_64a7c3cc333e2660ef8fcbc28f443cfa085f4faa47601ce6b925d97e6f2a8e8d43%不明1
157gpt-5.1-2025-11-13_unknownconfig_8b5491c3be63ebfdf517e9246d2ef5eec0787338aaeadbaeaf6d5316e49de14143%不明1
158gpt-6-luna_none 2026-09-22config_860c68884b4d4ab198f28e1301359d2ead876a14f27af884020f8332484f8c8643%不明1
159mimo-v2.5 release-date-unknownconfig_f3bc5dd6afb01b14076a26df6e2a0b6dfe7736211da999280e4239c3f5926d1743%不明1
160gpt-5-2025-08-07_unknownconfig_2a460ed4a4ca6de1d7d8e878909ca11ac0024440d524db07689139f155781e7d43%不明1
161o3-mini-2025-01-31_highconfig_e4182d3bb24702133a1774ec25e0d6ad50fbd9c93dca7fb0b4fb936ac783c66943%不明1
162nova-2.0-pro-preview_medium 2025-12-02config_c1afb4d3d186dcfb0a7a2dbae14282313fbc145f8637a0a2c7bcfe3c51121a5843%不明1
163claude-haiku-4-5-20251001_unknown 2025-10-15config_b52b218b85b2634fa04105db87a32de04aa538c93b99351d894658b8a6b4697942%不明1
164deepseek-v4-flash_high 2026-04-24config_35f47baa2f1110762c9dca07efa1422791b7a7d96bb69a60df3e308304c77bfb42%不明1
165glm-5.3_low 2026-08-14config_a30e2dbca4147e12411918f8fe27b482acf83bfb82474555e97b09997f7c4eaa42%不明1
166qwen/qwen3-235b-a22b-thinking-2507 2025-07-25config_f65eacad809480c5d16bd941054fe6438d365ad2e7146ae25e3b58307a13cce641%不明1
167gemini-3.5-flash-lite 2026-07-21config_cd4b9ecaee2da72560e9d37627ea3673aaecf8e9f677e19099622072d109d98441%不明1
168cogito-671b-v2.1 2025-11-19config_81713fa14591c58e9fb5ea75f0cea65db071c4f219654a8a7ac7424cc799ca4741%不明1
169qwen3.6-plus 2026-03-31config_ba187e15c28e9dcb5bf3c4a6c1ae54e87ed4e2d6c30dc01a778ccb48a17de50141%不明1
170trinity-large-thinking 2026-04-01config_188bc4dc2e65ef50be534bf6fa49dc10551fad8ec4bb95693bc7f3d64dbc04a241%不明1
171gpt-5.6-luna_none 2026-07-09config_6224d05383bc48cd3bb6b59d9ea9e64a3b6d9fe5872c8af125eec337c81c150740%不明1
172gpt-4.1-mini-2025-04-14config_6b85e11f7ab1ef935099dcca6871f92a6d903d7f57eb2b91ea9b4598d533d5ae40%不明1
173nemotron-3-ultra 2026-06-04config_e433fc48f41447d0739be78ed3ccbc594d0a744da877a350c22483de9195211b40%不明1
174mistral-medium-2604 2026-04-28config_4e5713daf77202aa06a42f29e4d949737d45ab429402d01fa166118cbbccf61b40%不明1
175gemma-4-26b-a4b 2026-04-02config_3f1c545a55462aa7cc63b40a36d332857ea8e7747de5cd63da7f0fd6b244922a40%不明1
176step-3.7-flash 2026-05-29config_43ced50d4366da53bade6032e3f34a196c33ad7aad0caa5ff56f24abe5a8f4ef40%不明1
177qwen3.8-27b_low 2026-08-14config_4ed4a245e86c3b35bdbdc3089544118cc326779713c336eba39094206218127640%不明1
178claude-sonnet-4-20250514_unknown 2025-05-22config_7dc87305abb3ebe9d2a98e595e01049d9ca214dfd79be3726a13addcdb0146a240%不明1
179deepseek-v4-pro-0813_none 2026-08-13config_5fa160d2179328adbefa23b2303c62f3c5a4d70adccf9198117d69bb8b650f9440%不明1
180magistral-medium-2509 2025-09-18config_522ad7ac268e3523a0b75597a349125b923f956d6994489847634c71a35f7c2739%不明1
181gpt-5-mini-2025-08-07_unknownconfig_5301094fd5f5ddffa482b7f86d87bcfcc9ceec55481e2ec4dc8c4e4de08035a639%不明1
182qwen3.8-27b_medium 2026-08-14config_0108af336df67bc61942474da3480ee226f8181346a573cc6dea33c23dc977f139%不明1
183DeepSeek-V3-0324 2025-03-24config_23bb0162ff1536ba7325eebf284efa88aa13b1b7830d459bb70e8f3ae451e2af39%不明1
184gpt-5-mini-2025-08-07_highconfig_caaf749bf4753407486a121bc37901e63701ec10b5f7aaa237fef1323661097a39%不明1
185DeepSeek-V3.2-Exp_thinking 2025-09-29config_6156beb18892bed933396e6758c2bfc7ab0fb8912e9b7971d38722f38f1cf22339%不明1
186gpt-oss-20b_high 2025-08-05config_cf3d9013ecc7e45b9a6f893d5cf9ee343104bebb177dc092ffac7614aaf0513239%不明1
187mercury-2 release-date-unknownconfig_a91752b46680fd924fe1b0b1c99dfdfe1d42672eb8d1647ead9e64733427507039%不明1
188nova-2.0-pro-preview_low 2025-12-02config_e208597df5d4666c10b0c0f84f17a406a9b752cf6f506767458916e341aceeca39%不明1
189command-a-plus-05-2026 2026-05-20config_5493facb85dbb26d691725454952fe078bbd87146c0c24775bd2cd520464917a39%不明1
190mercury-2.5_unknown 2026-09-08config_692d3a7f6fbd4d39d737e999ff635c2c9e05588c1472f3dce1af7bebffd2489439%不明1
191glm-4.6 2025-09-30config_81d11e6642bfd30b4ada219aebe5cf98871e21289a9cf211a4140d8ca2cfe6c038%不明1
192DeepSeek-R1 2025-01-20config_7afa399dfb44106d86f16805e28e2cd12eea7ca40c633bfa59fc294ac49ac97638%不明1
193DeepSeek-V3.1-Terminus 2025-09-22config_1a01d1e19901054f66be56a4eae790458b0b4c6cb7b965c62d14903a4eb588f438%不明1
194qwen3.6-27b_none 2026-04-22config_e8510459f7c9464b252d9fa5007035686d441f03e0e106c9267c866cd9d769cb37%不明1
195qwen3.6-35b-a3b 2026-04-14config_050cb6baec8daf05b2f6cb82f435bad28f9126f2e06f6747616a824ad953baba37%不明1
196mistral-large-2512 2025-12-02config_a64c2db86ca74d1ae45a6d62a8ab90037d6857a6e800cf9ee4e530a483beaef737%不明1
197qwen3-coder-next 2026-02-02config_600578749286bb50d3412986980029a49b12ce3e4b9fcb44c49f5d22c9a2282936%不明1
198qwen3.8-27b_none 2026-08-14config_8faab16bf0dd6906e8159a8f9cc3dd049de2b2f9ced9f3c2bd6b5a868187c09036%不明1
199glm-5.2_none 2026-06-16config_0879f349206e030c802fe410aa3c803e0c1c1c8bcd2a4161d4396dabc82138f736%不明1
200nemotron-3-super 2026-03-11config_46af45918e1128ff007dff07f810f712b55fa57bc3c94598a9657952ab5f22fb36%不明1
201openai/gpt-oss-120b_low 2025-08-05config_5efeadf639159b56101e9ec27c9c5e1440de969d0973ddbaa6b637906aec884036%不明1
202DeepSeek-V3 2024-12-26config_bad7c38702fcc9b2074f85ebe36cb005cfa52392bb54f670dc3fadf655301aa136%不明1
203qwen3.5-122b-a10b_none 2026-02-24config_48a043346f3837173faeb7cf95698771d0ccb9e3e65d828bc7ec8232275506b936%不明1
204deepseek-v4.1-flash_none 2026-09-09config_17190ce708a3578440abb75da28378cf5b992baa86dd754b1522cc7abc4f03a036%不明1
205Qwen3-32B 2025-04-29config_0e299bb5ddc73088dbdfedaa5ad96fb9732811f115f58fdb54298ff8f9a88f9835%不明1
206magistral-small-2509 2025-09-18config_232e116cd28cc4d2e0faac8ced4f80da93a6b798ffe66809ac21749fa2d59eac35%不明1
207openai/gpt-oss-120b_high 2025-08-05config_66f7844fbc15e2acd3d9fdcd1bcc34f27bc63c116f3aef016899865d4ab68aea34%不明1
208qwen3-30b-a3b-thinking-2507 2025-07-30config_3f600e20b035a28ca264beb701cf9ad19526a7e8ec5c5bef34e72618799d7b5b33%不明1
209mistral-medium-2508 2025-08-12config_a9507a14d2181b09c54f36c4f3953de4a33cd4fe4f054f3c99eabe2d5bf1515132%不明1
210Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e132%不明1
211qwen3-14b 2025-04-29config_5e352c4923f4422a53c4de0b5d9891c078afaf2e4be4e40cc11b9c4701f8c07432%不明1
212qwen3.5-9B 2026-02-24config_1d4841f3a9d99f6af9369d0bc707e19b00ea38053b4704ade484342a4e7c46cd30%不明1
213qwen3.5-35b-a3b_none 2026-02-24config_63212679a488a043f4fee7b2530654eb3617356a8c01fdd8c9cde11fc25c90d729%不明1
214devstral-small-2512 2025-12-09config_b56f55c736f65f3304afb2f87d95c059d055242417a84131397c7458a679dbb729%不明1
215nova-2.0-pro-preview_none 2025-12-02config_70dc8941324f746c0145c24b1068f8b230e46bb5686c93d18f280d9304eb819a28%不明1
216mistral-small-2503 2025-03-17config_0db03531b34465e4293aec44c885da8d0059d695abff9f224df7aecfeaaf42ff28%不明1
217claude-3-5-haiku-20241022 2024-10-22config_bc1c788c15732e087bf0e04531cf315be0ee2ae8d09782928fa8c9315a69b20627%不明1
218mistral-small-2506 2025-06-20config_266970c38c96d0a36822d4c2a09b64dd0fba1f2a4ea6cc1e38cfe419d02a573126%不明1
219Llama-3.3-70B-Instruct 2024-12-06config_f283f7089dd453a21e2b322ef1b005f773c5a0408f3a7bd775ce7e68d436e29126%不明1
220gpt-4.1-nano-2025-04-14config_57a526430c1497f79df3593e90e3bc790196748862930bec1584ccbf2f83239b26%不明1
221mimo-v2-flash release-date-unknownconfig_9f11e5e35c5e8730cfa7f076094217138d2a92aa75a484e95fad117608fff63226%不明1
222granite-4.1-30b 2026-04-29config_4a0ceef991c9b27047dfa9da454de8ef7d3d95568a05fb381a7678eef3fb8c7b26%不明1
223solar-pro-3 2026-01-27config_dbe246b352f24f96a11ff7f0b3c83dd81214f11bcc102ba85f161d970cc8854125%不明1
224gemma-3-27b-it 2025-03-12config_0f46612c63e309c62273adb8953f8aacd2cfc08bdde8a59736396b32c353725b23%不明1
225qwen3-8b 2025-04-28config_b038ff236370c0673c8385cf01423d8f6b8e3204cd2fce92c2175355b68c0fa823%不明1
226Llama-4-Scout-17B-16E-Instruct 2025-04-05config_b21d653692fee94a640375573b07132485c5da4479865700f91c67bed9cd893d21%不明1
227gemma-3-12b-it 2025-03-12config_82323d495f30d6abb0efbc148e7caa6ee0fce1566a4b87060e4b7818237be91416%不明1
228Llama-3.1-8B-Instruct 2024-07-23config_ee87ed8b6981548129b73849dcd7fbcd8975d48ed86ddfa4de194159c1cc83a013%不明1
229Phi-4-mini-instruct 2025-02-27config_ec2fd6c7bc33682545d26d505f4acc66129205b66e0817cb96f1a9be4d3a664c11%不明1
230qwen3.6-35b-a3b_none 2026-04-14config_d9b262eda59c0aa5a54c6dbdc9f8f4634f1f23832a865eaab974809a4079c0b61%不明1
このグループの構成を比較する
上位セットを定めるための独立したエビデンスが不足しています。
  • キャリブレーションが検証されていません。
  • 独立したベンチマークファミリーのカバレッジが基準値を下回っています。
Back to all kinds of work