Reasoning

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

Solve novel multi-step reasoning tasks

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
1gpt6astra100.0%2
2gemini38flash85.6%2
3gemini3propreview51.1%2
4gpt5pro38.8%2
5claudehaiku5532.6%2
6gpt52pro31.4%1
7kimik2528.6%2
8gpt527.2%2
9gpt5125.2%2
10gpt5mini19.9%2
11o319.1%2
12o4mini14.3%2
13gemini25flashpreview052010.9%2
14claude37sonnet7.3%2
15gpt45preview5.4%2
16llama4maverick17b128einstruct5.2%2
17gpt415.2%2
18gemini15pro0024.6%2
19gpt4o2.5%2

モデル構成 · 直接プロンプト

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

エクスプローラーのエビデンス

ARC-AGI-2

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

RankConfigurationCapabilityUncertaintyFamilies
1gpt-6-astra_max 2026-09-03config_459ac8dc316851dc4e50c105aee8cd97974594979a58b278e5fc558abc01696a95%不明1
2gpt-6.1-sol_max 2026-09-29config_b43cfb6409de530a548099d6e799fa06d4e40cc964681a2a293cabdb9984797694%不明1
3gpt-6-astra_xhigh 2026-09-03config_01fa4b20161c1bdf682ddb566827c57cdf4c6af2840694fa8d27a1ef2975397693%不明1
4claude-opus-5-5_high 2026-09-22config_7d6b22134e67c5c3cbabe16024f67eaa8d2d0028beb38c324eb6aa1363ef464a93%不明1
5gpt-5.6-sol_max 2026-07-09config_754c0ab021ba6f8a46654f4bb97ea19533aabab5920731757714e1b600fb019c93%不明1
6claude-opus-5-5_xhigh 2026-09-22config_8d844d418af40e1b2e2be2417ec7c705d393f0614fd73b59315c80b28eb6f94093%不明1
7gpt-6-astra_high 2026-09-03config_4a61134a89c8c322be80e423e6dad2ee46a2757c726c4d035f9985eb2118797c92%不明1
8gpt-6-astra_medium 2026-09-03config_4b222f5741b250aed06a506403d08dd0234e0cd90b24a24f9a33b8fafe0a33b992%不明1
9gpt-6.1-sol_high 2026-09-29config_1f8bb9cdde7bb4d960d11b71b5397d70d937ce9543309f6194a6d5537b70b0ac92%不明1
10claude-opus-5-5_max 2026-09-22config_8c9469fb0c79a91ec7f7339631f7a41a866bd351cc8cca585db3b09da43f805592%不明1
11gpt-6.1-sol_xhigh 2026-09-29config_c14e9a16ce3b67838a01c5fa0ae1c1e76ec609d8a919d4c4d1491d975e3481ce92%不明1
12gemini-4-argon_high 2026-09-30config_207f9c411d59bcde3bf970e7af83b7b5f6288b7dfbdef7e1a2ad4ee5dfb97f6d91%不明1
13claude-opus-5_max 2026-07-24config_5bca1297b30f2dd722dfdb818565823ac3180a4c7f32117817c77367563f863b90%不明1
14claude-fable-5-1_max 2026-09-01config_20d24ff21090d461494707eb0ed4633e918505be367c5191e52636dcc9cbf8fe90%不明1
15gpt-5.6-sol_xhigh 2026-07-09config_a6212bf3d85efd40676193246413c07f3e96545c5f9184d0e3a6a696eee0d61a90%不明1
16claude-fable-5-1_xhigh 2026-09-01config_ac459e99ea04d071a60495d458c8ffe2d614dd1d6415acd6193fda9b92a8f71790%不明1
17gpt-5.6-sol_xhigh 2026-07-09config_c5d87137affb18057458141a2201c1093e72c743adf2326fb6ff1ec20768df3390%不明1
18gpt-6-sol_max 2026-09-22config_a89bd445f30b3c6ba0948fca959b7de745da7aba56fa547de9f703d6f06b833990%不明1
19claude-fable-5_max 2026-06-09config_39f7206b2a3f48c00ae0256dcb233300e9af283b95f49ada037fd8b88406b2da89%不明1
20gemini-3.8-flash_high 2026-09-02config_4a24b550a22ac751cf70dc309ba28e0a8637c5d06c7c7ec8ed3209b6d5d425d789%不明1
21claude-fable-5-1_high 2026-09-01config_27766728e0a0bf7657bc8a5e76395ae8a6fd01b00e4c59c4981c16954910291889%不明1
22claude-fable-5_xhigh 2026-06-09config_cbb7a788c8497948fb5eb4bb21043cafea82e09549b4de3720e36fd183cab42188%不明1
23claude-opus-5_high 2026-07-24config_3fee4cb95a5b55d4119bb8a372b0881865b15e90dbdfef7f23735cdd95d29cdd88%不明1
24claude-opus-5_max 2026-07-24config_7a2113af2b6cd5388d95fd15d6436031ea32d56a965e132423fc0302fcdbcad688%不明1
25claude-fable-5_high 2026-06-09config_5ed5bcb342e8ab6ce8bc93bd0ea64a933eadc30b52e8c0b0c357a72b113bb0b988%不明1
26claude-opus-5-5_medium 2026-09-22config_acf13135e664996effa97a0b3c24ed2f9fc07bb7e4f6b666136b34f3e61a210b88%不明1
27gemini-4-argon_medium 2026-09-30config_70ad6983e428d059225933c75e0ae6c7371b552e744e3fc0c9147b3fc39b1eef87%不明1
28gpt-6.1-sol_medium 2026-09-29config_df4e2cbccd682a1407151d157cf96fb8759feba2f0a5cc7c3c4b2e0b7e690b2187%不明1
29claude-fable-5-1_medium 2026-09-01config_5354f250502ccf7d091af654f1a16a73f76f3fa88763b3680a58a4d077b346c586%不明1
30gpt-5.6-sol_high 2026-07-09config_09dd4673bc766c763c65d49d602d243472ca2f09b3aaf81a1d208d39495fbcf885%不明1
31gpt-6-astra_low 2026-09-03config_2730aa242fabab2a424069b63462fdbc8362e5ba5ceec28bd9cc4057422ee7ba85%不明1
32gpt-5.5_xhigh 2026-04-23config_7afd6634ea3788f264d7437df49085a9994ce79c3a242b2a89345da618b84c9385%不明1
33gpt-5.5_xhigh 2026-04-23config_b830a8bef566eaa2c4015bf50a090865d199e9dab6e498f5d8a7dfee9be2e86b85%不明1
34gemini-3.7-flash_high 2026-08-13config_33f22ae7a384cd21402e26fda58a9e657505aa8cadbbc9e8067f860321792f8e85%不明1
35gpt-5.5-pro_high 2026-04-23config_96521c0cc7fdbf001df890da67909758dda57f9352da6868f02cf9821836d6ef85%不明1
36gemini-3-deep-think-preview 2026-02-12config_fe8c3b03e939fb540a31049027dd4980a7a1935397371bcd49f046d35921602985%不明1
37gpt-5.5-pro_xhigh 2026-04-23config_5d70d7cbabb6eab6c6d7764c951fe4255bb7258098996cd903d8eaf22421f95584%不明1
38gpt-5.5-pro_xhigh 2026-04-23config_e8ecc274bfef3d506b4fbadd4d7a55a1d55549f4cba36c151094fcd8ace1872684%不明1
39gpt-5.6-terra_max 2026-07-09config_ee67687c955bc9f26fc4db66d5f2cc4b55b08ccc28ec113eed5e34df38deb85c84%不明1
40claude-sonnet-5-5_xhigh 2026-09-28config_aa99a1933f3d6dea131b23e6328e0953116656c349a04d829cb9873104a3cf7a84%不明1
41gpt-5.4-pro-2026-03-05_xhighconfig_0fa56b7c101efcf7fe44fe017dcfa86cc7bb31480b0545411a04227831f7fd0783%不明1
42gpt-5.4-pro-2026-03-05_xhighconfig_9030de77d4bcf89e2649dd6094966d47c92ae92e4fe342ce92e668b6e8ae4db483%不明1
43gpt-5.5_high 2026-04-23config_e5a59f69c290299c8fcec0331e4ddc88025c9d1e8c6bba4df7654586fdeb308d83%不明1
44gemini-3.8-flash_medium 2026-09-02config_c95b66bb9fb419e08316645d00bcdd46e7ba251a460914264205200ae50d153c83%不明1
45claude-fable-5_medium 2026-06-09config_be318768dcd05da8d6b29df2a772afdcea83e9b9dafb362d72f5230e1373328a83%不明1
46claude-fable-5-1_low 2026-09-01config_07e6ddbc981a7e823c17bad657c9f2219f44f2df6379d6494ee68a9344398db278%不明1
47deepseek-v4.1-flash-1017_max 2026-10-17config_86346a8a147355127f95ad4747427307541030b80b423cf4798676323e5fe55478%不明1
48gpt-6-sol_xhigh 2026-09-22config_e959c7bb557edbd4246d4dc44b76fdca6f2dc5cf3da444a05bf6ab250a89ba0778%不明1
49gemini-3.8-flash_low 2026-09-02config_9c599ae78680ea6d6aaa202c417f2ad8917745bff422f21c4a38932377425a4578%不明1
50gemini-3.1-pro-preview 2026-02-19config_2a4a841c7b914b1a8a2d25ab6e9eeb8accce14e7fe19f79cb0bd5724f23e65c977%不明1
51gemini-3.1-pro-preview 2026-02-19config_98f1ee35041dc71b596af09b1ff1f25a97e8f8eb9a2908995e51df6607270f6d77%不明1
52claude-fable-5_low 2026-06-09config_4a2b695eb09237203229707a3f6d88d91cf12ed6c15269691057e09b3b2d4eed77%不明1
53gpt-6.1-sol_low 2026-09-29config_59e6c749960e77b2a68d75c49415031c7264cf9ea310a6040dadfa232ab0a25f77%不明1
54claude-opus-4-7_max 2026-04-16config_8b5ace24a05b5c6a29201f3a6df807af10dfdadfd87f90d594bff89213802ff376%不明1
55claude-opus-4-7_max 2026-04-16config_9e768253f804f9aa257bb2909640d54cf74ef696e454265ac8303936197c36f976%不明1
56gpt-5.6-terra_xhigh 2026-07-09config_21757d060692dcfebf04f054b43775afbf68a295fc63a60c22afeaddbbf9898174%不明1
57gpt-5.6-terra_xhigh 2026-07-09config_47f7f8cc3d1917dad79a3f3ccb581424903d62ddaf92ea9c6efb1ebc56b523e574%不明1
58gpt-5.4-2026-03-05_xhighconfig_9ad540e2b10c3da26922fd48dbf4e330bd4e8bbae4a529f978777601e917fd7e74%不明1
59gpt-5.4-2026-03-05_xhighconfig_e9052ab8517a74b7ae787639204a0e401e49e965d65eab90ded6b2b768af031374%不明1
60deepseek-v4.1-flash-1017_low 2026-10-17config_6c291476da236513832ae64efa6ceb0e7a00d086f533686c2fc0d02e61c897fd74%不明1
61deepseek-v4.1-flash_max 2026-09-09config_b1be4ce87622385ace43fe9634ac8122744a407712260a0a80a85e4c4bcc8a9573%不明1
62claude-opus-4-8_high 2026-05-28config_2901e4a46d7c43fbf1304f3abb5dc5d7467a8538ace891805875181e7cc7d65f72%不明1
63gemini-3.5-flash_high 2026-05-19config_390526fd99a083b7192062a0cd537e06256b47ee7d3069129f616628b7cf8bde72%不明1
64claude-opus-4-8_medium 2026-05-28config_d344417ea43608d113dc50a3e182255034ba6958c07b75d57522add31ff5649972%不明1
65gpt-5.5_medium 2026-04-23config_af6b5690f3be09f0c3060a270b1749f2a1e54019ada6c5e7ce17dd889a76061570%不明1
66claude-opus-5-5_low 2026-09-22config_c5714ab805bb251ebf8f098ae25ffc54d1ce8639c6cf18a07c8e78ed221b439e70%不明1
67claude-opus-4-6_120K 2026-02-05config_a013a724ae41098d7580e39f8319fe8782ee22ffa4aab4b981644b90ef4a670369%不明1
68gpt-6-sol_high 2026-09-22config_cede3be5deb4df7e753b7817ad55218130ad31c0896193f50159949bb6c366a769%不明1
69claude-opus-4-6_120K 2026-02-05config_2c5135060ccc397a858ce204fc986700b811ea9464efca04349da5a00aea965469%不明1
70deepseek-v4.1-flash-1017_high 2026-10-17config_0b68380a3062efe72a3da9a79e199f04240723803ef4295dc76785070dfaa34869%不明1
71claude-opus-4-7_high 2026-04-16config_576b7240f1d8e337adb628cd156ebacdce9ba28739ed25bbfb6a6ac3e489634468%不明1
72claude-opus-4-7_high 2026-04-16config_d3c78a01530277f37306926bbc80d0735b46b3bf8aac1ce4fabfc474a488582168%不明1
73gpt-5.4-2026-03-05_highconfig_115bb099596ca7d5aa11f0202f0c5981302591bb21f538fe41a8bcae55b3d41c68%不明1
74claude-opus-4-7_medium 2026-04-16config_93aee180efa4479a1a8d1d64a1d0d59068071bad2b8e16ce14d062797c4e2a6468%不明1
75deepseek-v4.1-flash_high 2026-09-09config_c2e967ff608b20c5170c8b1c6b6408741c859c72b775159029fdb8279e3353e468%不明1
76claude-sonnet-5-5_high 2026-09-28config_e402cddbb62b45b986513130d3a39326f3645894a63bc84e7d0ac116da94166b67%不明1
77grok-4.6_xhigh 2026-08-12config_29b18ef8e9f7b37d951af9a5368d1e2b6969f58f1ab83935116074e114334da967%不明1
78gpt-5.6-terra_high 2026-07-09config_169ff121b1a860195c4831f3262a2fc8051385bae12512ec3561690f6ea9533467%不明1
79gpt-5.6-sol_medium 2026-07-09config_26692174c93318a353e8f900a3d0718cf761a0f3b2b1cd5d16ffa8205e82239567%不明1
80claude-opus-4-6_120K 2026-02-05config_3c41d120cc61bca5081d35a8893583423e0b7f21b99e4fa297957377da08db9166%不明1
81glm-5.3-flash_max 2026-08-20config_9e80e15ffac25288f9ed06975ad6e115c310e1ccf43168e90b511a5529ddb78866%不明1
82grok-4-20 2026-02-17config_b8598946b187d4457e88f112c3f8dbaab31fc7dab6fcdd29fbe4b94b9f8cd64b65%不明1
83grok-4.6_high 2026-08-12config_740edaa78ca55598fe4da4f3ec13156ec451e623fe87cd1c0001b17f4eb7830c65%不明1
84claude-opus-4-6_120K 2026-02-05config_3c805069257fb7fa4e1b77aca20a5d9361eca900c7c5bc8923406647b529e40365%不明1
85gemini-3.7-flash_medium 2026-08-13config_f23a2989c021a0521977017290b5fc5dadc083222007c07593dff7d1b7c0c21d64%不明1
86claude-opus-4-8_low 2026-05-28config_24717277bc617033c35888e1da1c6335395a378b37525fb5b5f2c7d998bd7a8362%不明1
87claude-opus-4-7_low 2026-04-16config_25456eb7ea2020bd0d8d243f3474eae341ee66a45cb758841559aa00cffde05262%不明1
88deepseek-v4-flash-0731_max 2026-07-31config_65747885072a9d795f2d8d1bc0e7497a43d4d5e9c6b5aff38be425192100db8a61%不明1
89grok-4.7_xhigh 2026-09-21config_eebf1180b6352b82c4649900294ddbf13c2ae5e97a5e4f79d0b1657aeedea4a661%不明1
90claude-haiku-5-5_xhigh 2026-10-07config_2b2d9d476805ac1aecdb33ef99a75b26c10284af30d643961b1766029d77a32b61%不明1
91grok-4.6_medium 2026-08-12config_9fac37c35da2df6f815eb842df6451185c8264b25a3d38e375c62efae452cad661%不明1
92deepseek-v4-pro-0813_max 2026-08-13config_b62b7a05e1a62d6b54026f563dceefeb675c991c86b329d264b1fe65d16c4c1f61%不明1
93deepseek-v4.1-flash_low 2026-09-09config_0131305041651f4439f78094c275f9d821ccecd6061845ffb61ead9d7934f49761%不明1
94claude-sonnet-4-6_high 2026-02-17config_9ab5c6ec8596b85cf302601ed53f374db8efd607ba97e75af0029519ecac60e560%不明1
95kimi-k3_max 2026-07-16config_d707a33ef8e8b94ed2cdf47b839b4e654183a727a95543e4e877618d832b211260%不明1
96gemini-3.6-flash_high 2026-07-21config_db4a45c2def6fe6e591043d15ed89e65b5205501b8aae28cba7a0e5283b3797760%不明1
97deepseek-v4-pro-0813_high 2026-08-13config_929c2e5f1f6ebf0b3227cc7a580b2e7a8d0e7a32cf1cb1de16a37c56148c3d5960%不明1
98gpt-6-astra_none 2026-09-03config_0f9ba9bba4bd6d65bcf2c949b713d195713aa4635e9fe3a253804962e1ef579f60%不明1
99gpt-5.6-luna_max 2026-07-09config_e587502fdc3b99d900e303059a9701e54e761d87c3795cff54c722c68dfa0a9060%不明1
100gpt-6-luna_max 2026-09-22config_094f403a72365841df9ab1f46c22fa61ac61c04909e6b2e2f0ec085342959df459%不明1
101grok-4.7_medium 2026-09-21config_4792661fa6fa6d674a3c30217e9944cb4fb51b7efbf1a06d952b6a564e3dd94159%不明1
102grok-4.7_high 2026-09-21config_59dc2870d2bf7381d4a12e03744ce477788ae035bba67cf1d0fdf5cd443929af58%不明1
103claude-sonnet-4-6_max 2026-02-17config_c433e7b9c596564e10f4113916700ea60ac13b197f2d7cc68a05a2078e7a303658%不明1
104gpt-6-sol_medium 2026-09-22config_7b8e8339811e7cf29e87ab4a75379ae6b6acc970f2154f720cf53b3f76854dba58%不明1
105Muse-Spark-Open-816B-A42B_xhigh 2026-10-15config_3df194f45052950e8bb152b0f3a268747fad2113d1693c97eab899d1233b5f4557%不明1
106deepseek-v4-pro-0813_low 2026-08-13config_7a951c994ca4cc1835d9319ed61152e73e8cb76f5b7e792f25adb0ed7cbd3b9a56%不明1
107deepseek-v4-flash-0731_high 2026-07-31config_f7a9261779df7da9a677c86b67a9d9fbb2e3c6cce7e7972382fa2a26a50ac23256%不明1
108gpt-5.4-2026-03-05_mediumconfig_58ccbb8154d77e5c49d8bd895df025b1d5fba5cefefd8ec0bbc2a406d8f875cf55%不明1
109kimi-k3_high 2026-07-16config_fb243b451243979dea9599d64ee045512cad795f0a703e57e8c87c1eb99b94a955%不明1
110gpt-5.2-pro-2025-12-11_highconfig_70286df95a057e62644c7f7efa5e97bac8639178d8b86e799023ceb3738376bd54%不明1
111gemini-3.7-flash_low 2026-08-13config_349173cc48ad97cf0b137ea9e01e45e27bee6511c30cda942165dd14e7add43453%不明1
112gpt-5.2-2025-12-11_xhighconfig_1cc8838aea2fd625ac3891c32d87a4dcbaac8a1248d85193220a4e61374dce4b53%不明1
113gpt-5.2-2025-12-11_xhighconfig_3b673dcad3a76f543b9308fe815701b7011ddc7eadfe4ddc74c137f6ded883b853%不明1
114gpt-5.2-2025-12-11_xhighconfig_9bd4af1c2e247f626d878134c179bdf0c8ba58516464f224b82ed263f4cde90153%不明1
115grok-4.5_high 2026-07-08config_6627d3698d23a77db1377ba90223df3c8b40d39fef1961f8a668172f3084650353%不明1
116grok-4.5_medium 2026-07-08config_aa5808b61a36fd59f4d4e7204c16d938fd5a6c8a53dc0e10a725217c7b3b56e253%不明1
117gemini-3.6-flash_medium 2026-07-21config_99750ef5b5dd571ee570fac195e80a1a3a8d7fd1fb2d31bd5d71e5f071396de950%不明1
118glm-5.3-flash_high 2026-08-20config_4c0f9b961e395b1791f6057b2a518013bb13d4fd8cd2b12cd9c4bf345d3f53a550%不明1
119gpt-5.6-luna_xhigh 2026-07-09config_15ab9e2f092a10508d3e82acb34ef1fae3615d15f0f416e77b1232d8d89f7d2348%不明1
120gpt-5.6-luna_xhigh 2026-07-09config_1ae7e4d090d373a31478ac4e1034d451bb404f33f81735ebd552818e51a37b6a48%不明1
121Muse-Spark-Open-816B-A42B_high 2026-10-15config_452e6458c018b8b8e159c42cbaf2c383a831e6f96fbe833a4e11365ced24b27348%不明1
122deepseek-v4-flash-0731_low 2026-07-31config_e1479e5d25438dfb1ca10cf178967f19d3f7b22f64aab9335111b72cc9a2673d46%不明1
123gemini-3-deep-think-preview 2026-02-12config_55d25ad5185a0555739d8fc373edf98ede9c96137e5cc3df02b035884dc9cf4945%不明1
124gpt-5.2-2025-12-11_highconfig_c902fa5dfe9449b34ac52ce34345dcbf410cca4afe2a9a22905a8382ebf7202543%不明1
125gpt-5.6-sol_low 2026-07-09config_a144462859844e2b3836fc10c764249d8f7beacdeea07e54303302202497d4cd43%不明1
126qwen3.8-27b_xhigh 2026-08-14config_b53024c1425b01063100803b8221fd98fe2734df15aa00117eb7e8d38f04df4042%不明1
127gemini-4-argon_low 2026-09-30config_6c80e8c2a7b1bdce6aa672e08a8ec939bbf914f0443995003cc6fc807edfef9d42%不明1
128gpt-6-luna_xhigh 2026-09-22config_6a394e57ab1ac324e17dce833d85f7eac02411272aa396807af5c0c8fd3dd38342%不明1
129inkling-small_xhigh 2026-07-15config_173d36caa3ea41263da1ce48df909cee87da8ce2920290487f50960e300acac940%不明1
130gpt-5.2-pro-2025-12-11_mediumconfig_222b23971acbd7d18bd370e8a7a35aeb7250868622f33309a71d48e1b380e0c038%不明1
131claude-opus-4-5-20251101_64K 2025-11-24config_df1b8c7d44d387c2098bd72d816a90b819338a07b2c41ea8f0e1b0e173292c0b38%不明1
132gpt-5.6-terra_medium 2026-07-09config_0d4e5a2402aaff31642ebd7721b23cab7eb8b1609c31e74acac46dfba223c11838%不明1
133Inkling 2026-07-15config_a2d04d678e4ebc1eb55c791400f25c4a099721ebc4d0bda05c4dab68d22f13cf37%不明1
134gemini-3-flash-preview 2025-12-17config_c5cf4d3a0cc1ac0ad48a1c3059ef240e4b36661f1442687bb216a78c20a32c6b34%不明1
135gpt-5.5_low 2026-04-23config_5ba66f8f64e7abda1eefcca714b2a4e29e6df336bbcc02a4f6eef6427dec0c1733%不明1
136grok-4.5_low 2026-07-08config_25ea5badbe63fca576b088b55eae5c563282b7bc22bee0c3e359a874b8307a7133%不明1
137inkling-small_high 2026-07-15config_86fa604e2d39ede6f49c1d2922a1e91372fbd5e3409ef6dcc8d80eca89c9822333%不明1
138claude-sonnet-5-5_medium 2026-09-28config_ebb63275757610d0c8bfdd030f93c503b97d3814bd399bb1c4d2faea122f0cf433%不明1
139gpt-6-sol_low 2026-09-22config_07edbaa3e394c3fb46319648c01a6548fd7329cbef16deff411a83e81966b3ac32%不明1
140gpt-6-luna_high 2026-09-22config_572094e4a437a964e8cdd9baf543b8707332e7d40676f47168607b00c4b8c78031%不明1
141gemini-3-pro-preview 2025-11-18config_02b4f95f319f40dab248ced8ba29f4607359351dcda054995f1fc3c43ab57a5d31%不明1
142claude-haiku-5-5_high 2026-10-07config_eee4da09dbac8555553bc292fe1030f06ce59b5d700fe80048eea68b4dc2aae631%不明1
143gemini-3.6-flash_low 2026-07-21config_17d84a71f9462c5c0853b90d7557e0c6563cfca83f6dc0bddf0b97c76466f3d030%不明1
144gpt-5.6-luna_high 2026-07-09config_6028644d4e821f0579c6cbc821b016bc174f1f7894f663314e8af46a81ff60f129%不明1
145gpt-5.4-2026-03-05_lowconfig_9af476f4288b7b9ae7f2cd146e5bbc30b562e3d1130e657f885b5a72d9d3665429%不明1
146glm-5.3-flash_low 2026-08-20config_e585850ca02297c0a86750b74d671471b3d13eecbee0de0402892505855c400a28%不明1
147grok-4.6_low 2026-08-12config_abfa7afa2b24605e220da4c04163a9159ff9d55db5a093c00026959a676ee88428%不明1
148Muse-Spark-Open-816B-A42B_medium 2026-10-15config_9a2cdc98d4ac765f7fe241ca380108210b0a93b838d12851d4dc37d06a3c192628%不明1
149gpt-5.2-2025-12-11_mediumconfig_74284bd9f08284b0b766cb218d6609ef15fe359b04871c0f5fb7c57289a0100727%不明1
150claude-sonnet-5-5_low 2026-09-28config_de3a120d7a85503e3ecc361f1debffe250ace2c05eaf745488e892ea5218e4cb24%不明1
151beam-1.0_xhigh 2026-10-05config_9a6ca648f922ba73366c1bb39c3ecf4eada96e9baa2a09bdc88db2973ae99c3823%不明1
152claude-opus-4-5-20251101_16K 2025-11-24config_6bbce85f5b3fd99c6ac3b40d5bf254dc0605a7607b2184830740eaee79dc615523%不明1
153qwen3.8-27b_low 2026-08-14config_38bed0932c151bd1b07ec2549746d531a28fa7b14fa5ca76a5da16f46916d62523%不明1
154glm-5.2_unknown 2026-06-16config_ff23a2838211ff13843b33b3bbd03488292be316658a70da82938693b6d2a9bd23%不明1
155beam-1.0_high 2026-10-05config_5a86bf0070ad98aaafddd6141a404f75dd12762ee579760faa90bcdeeead6b9020%不明1
156gpt-5.4-mini-2026-03-17_xhighconfig_624731a68cc6f43197ebf1496da288dae8aae258acfd43b0a6a7f0a9ce50ae3019%不明1
157gpt-5.4-mini-2026-03-17_xhighconfig_7d3ae160db3d1d396f01251dd2e453bfe06631afdf6722b8ebfdc6b03845f59d19%不明1
158gpt-5.6-terra_low 2026-07-09config_1ca335de2c353f962770d692fbdbde405136c4651fc7ffb237e919fdf5e16f7419%不明1
159gpt-5-pro-2025-10-06_unknown 2025-10-07config_498862ea9473f95b4002c6d02787c62f66cb2cfa78dcfe3920afbfbcd2c2c0db18%不明1
160gpt-6-luna_medium 2026-09-22config_287bd865fe379818fbb256e3a010d2e31fde1366ec4f27f72824561ef4c85ef918%不明1
161gpt-5.1-2025-11-13_highconfig_56e6155f909f76dbf0113a300a2987807995332ca3cc9485d4c741dae3fe649b18%不明1
162grok-4.7_low 2026-09-21config_89e24dadedd1547e720a7187ef1f0fafe6f9921cee884413f90ebbe75b7743a317%不明1
163grok-4-0709 2025-07-09config_bff840fc356c7c3470b6318f52c90859b4692cfc124e6aa8665f1a8279252fe616%不明1
164claude-opus-4-5-20251101_8K 2025-11-24config_a5f55c1ae90c6f1e9d98f88254ae875208125850c3ca6dc8494527cb4cc16f7c14%不明1
165inkling-small_medium 2026-07-15config_a9733e101ee5d6ec5cac420d76b14e986ac94801ebc089cf5be24ec92c3f634614%不明1
166claude-sonnet-4-5-20250929_32K 2025-09-29config_53daa4f20a8637cacbe2092213c824730106d0610a2aae8ebc4eb9dfbe8cdf4e14%不明1
167qwen3.8-27b_medium 2026-08-14config_050416b48f418cf6e0ba4e48fdc433ef285b15e9ecd9930bb277b49e02fe82f113%不明1
168gpt-5.4-mini-2026-03-17_highconfig_3c50f9a5d27bd8f0b2ef96c6ae8747c533fcf232aba7fe339589e6e47334f40813%不明1
169gemini-3-flash-preview 2025-12-17config_4dcc90ef06dba7c7866525cc6df1528d4fa2f36c69397a64374032f07e9b4d6513%不明1
170kimi-k3_low 2026-07-16config_6958f9c23200d1d6d10fbac93b3c78d531c6ec598604eb85f1ec2d293445ff0112%不明1
171Muse-Spark-Open-816B-A42B_low 2026-10-15config_d67f60dec164c6b5171a64861a59f3082af35a2c4baa62c8eb12d8149f16b3b312%不明1
172kimi-k2.5 2026-01-27config_bde253257a79ed79bc1615543f3e0d2dc6ead302f2f0b16ad54fd2d160c9ffce12%不明1
173gemini-3.5-flash-lite_high 2026-07-21config_901ad1303c9c31f60eaad7432884576f257ac868caa98cebb17b19ffe6a098a310%不明1
174gpt-5-2025-08-07_highconfig_2e3e5b6612e479d838606a6dd6ae863c5557bc73ab47fc8928357b9b11ffe03110%不明1
175gpt-5.2-2025-12-11_lowconfig_ed33ae702b784bf1c563d128a99bccdc840482ffd40dab893e3db384bc1917b610%不明1
176claude-haiku-5-5_medium 2026-10-07config_922cbd0c002847f047e02f49ddad5d92694375fec788fbcfe97687c2914047729%不明1
177gemini-3.5-flash_minimal 2026-05-19config_3aa8a5558bcc47163dfb63fb4e5504d7958d25dafe4638bebc8961613a97e26c9%不明1
178claude-opus-4-20250514_16K 2025-05-22config_8ec5f1c2a1be3bec1a36b956a31495e0a38aac720e6c0b9f24a3d0ca7494662b9%不明1
179claude-opus-4-5-20251101 2025-11-24config_d15abd72cc925522d52e1a39aaed2359cf359d89a08c5b44a6b63c2fe2bb25938%不明1
180gpt-5-2025-08-07_mediumconfig_dd301de319f6e39caa709e27e518b4fcaa82f9a36e022e94c6e8d8a1adba7a987%不明1
181gpt-5.6-luna_medium 2026-07-09config_23b1b1ada3c318e22831143fced18c5f9115955751b3090d82103681b08b88627%不明1
182claude-sonnet-4-5-20250929_8K 2025-09-29config_17f6f66c115d4b83681c4040610d9954d9c6b8818923f4d3b0fc117a633fe18d7%不明1
183claude-sonnet-4-5-20250929_16K 2025-09-29config_24cbf77041af70a66a70128985bbd7c98266bbcb7630e894f57f1767e56847f17%不明1
184gpt-5.1-2025-11-13_mediumconfig_19afb259ef5f60fbb4adab23aecda63fa83de6adedca537459880663e914d14f7%不明1
185o3-2025-04-16_highconfig_c2d6cfbd0a94956851698b38478bfc9eb4425f89214116fdf43c3fd7863af7227%不明1
186beam-1.0_medium 2026-10-05config_bf7d7e592df9c5ebc73e015602b286fe82c6c9702bfeef22a8d39f2b953ca50c6%不明1
187tiny-recursion-model 2025-10-06config_496259b66893124294abf85711cb542685ac4954c42a14fda67e728d01001ce96%不明1
188o4-mini-2025-04-16_highconfig_c0ec93b5c64f4c950a3f4b608590da18fb7b6610f2bf050b83eb8524dd4be0f76%不明1
189claude-sonnet-4-20250514_16K 2025-05-22config_c07f33143bff33af6280ef9bfe66cd9a188bee941b12af0fe346d2c5963dae196%不明1
190claude-sonnet-4-5-20250929_1K 2025-09-29config_dde2d040a590fe588244d1a4a1887fa6f3fe6df860ed5bee501cbc98c006b8106%不明1
191gpt-5.4-nano-2026-03-17_xhighconfig_74f74f43071a4d6ffc92d8e12bf1ba4d9a5927068a5537160205b71b958015b56%不明1
192gpt-5.4-nano-2026-03-17_xhighconfig_edb42e08dcf1226f01383a6338985b84d6b372fdb65f9606aba0d1dd16d2851a6%不明1
193grok-4-fast 2025-09-19config_518b0cfe940bba68d4369ae13ed7baeec4104ba3914ce3ab7353a712bc19fb355%不明1
194gemini-3.5-flash-lite_medium 2026-07-21config_496bd9cd1b2fd54fcfa216e45b607f0244a55628a4aa92a08340a34c1edbb99c5%不明1
195gpt-5.6-luna_low 2026-07-09config_e6ac58dadc7a9a4b0e1e46d1b8971b6a6d9281bfda7e67ff0bd38f457794daeb5%不明1
196inkling-small_low 2026-07-15config_5fef7e5cf1274a1db8f73f6f3fbdcc38950ed1895b64413e3f0191f92a3b570c5%不明1
197glm-5 2026-02-11config_17adf8e138bc6b475c6b315200a9260ddf510879ee4724f852ada5053c73ab0a5%不明1
198gemini-2.5-pro_32K 2025-06-17config_817294017ccabd93e3c06154072b902c8252ed4655c13f2c0975f5bd68fe32a45%不明1
199MiniMax-M2.5 2026-02-12config_f00ae7bcba118364b90fc9b9a0df5dd273ef0c8290628fe699f215bbb6eeefe95%不明1
200o3-pro-2025-06-10_highconfig_f44f52e8fd573c795447b5df494a4bf5a5e41b22b612b68e667437718a46f37d5%不明1
201gpt-6-luna_low 2026-09-22config_dd54c70b7aee8c8d54cd45377c8d963079eb38f90cdcbde58dd49822cf42a86c5%不明1
202claude-opus-4-20250514_8K 2025-05-22config_59c0a6dedc17ef8da155763e34cea17b11bb5da2aa7416fb32990b0177ae7b085%不明1
203gpt-5-mini-2025-08-07_highconfig_4fbd1737c6a3b53bc29f96420781b4d91365b1307fa687dfb52b7b124a15dead4%不明1
204gpt-5.4-mini-2026-03-17_mediumconfig_54644e87a30fa13abeadb8763c27c8c0bdcf9f183a489a87b6024f4a0ec91de54%不明1
205claude-haiku-4-5-20251001_32K 2025-10-15config_0f3f2b1a0d60e8b6a27b16cfce8bbd42f6d576f350943efda7a52276f8a4c46a4%不明1
206gemini-2.5-pro_16K 2025-06-17config_567903eee4b5954fe37316a7af1f0dbe8013f57f5f398cb08c9ecd4dc8678fc14%不明1
207gpt-5-mini-2025-08-07_mediumconfig_7904c047631fd36e887ceeb2f7e44b1058892e9d2ae63cb328e88d802758f8bf4%不明1
208deepseek/deepseek-v3.2 2025-12-01config_c516999fd8d25aee770ae07ae8709af8f34ac7baf73cd39413d5a84d65c059fd4%不明1
209inkling-small_minimal 2026-07-15config_9c591e27477571ae46d44dfd5a325db3ac97b41c1008029c410312e211652be64%不明1
210claude-sonnet-4-5-20250929 2025-09-29config_776fffa5b50b5dd93bba35760ca6ac22eab41e66ad5f82d92af73a04af1ecb214%不明1
211gpt-5.4-nano-2026-03-17_highconfig_231347245ef952db7ee1e5db6595a3692b1138bdb0c92b74492fa9a90a2b51e94%不明1
212gemini-3-flash-preview 2025-12-17config_6003ac5bf92b96020fbf11933db065a5848da8a7e51e47da6f4f05b619a7385e3%不明1
213o3-mini-2025-01-31_highconfig_e4182d3bb24702133a1774ec25e0d6ad50fbd9c93dca7fb0b4fb936ac783c6693%不明1
214o3-2025-04-16_mediumconfig_2e69abe4ea1cb466d658cdf09c49cb532d2acb5fcc5c3458a90e55d523b3f93f3%不明1
215gemini-2.5-pro_8K 2025-06-17config_ff6b1ebc99664f6628661d5ff5763e1eb379a36d8b36ad671186efa4aa32a8453%不明1
216claude-haiku-4-5-20251001_16K 2025-10-15config_bac57ca63ea1280337b6aadfc0abb34e402328bd5442c3880be38940c47184443%不明1
217beam-1.0_low 2026-10-05config_3d12cb61b21d357f2ed1802aa15bf49620793ca7cc2720af7275687a1de52f593%不明1
218claude-haiku-5-5_low 2026-10-07config_6683f2646ba6f03e4e9a39b1517cf4731f80cf6b86042c4936fd0afe0a28bb733%不明1
219gemini-3.6-flash_minimal 2026-07-21config_60e8189b6a9766ea0ed6d50db9bd88f25da0c93ad33312e80de5530aab01b76d3%不明1
220gpt-5-nano-2025-08-07_highconfig_e474cabd7951a6dac7c51123316397c395956931aa18a7b921cbdbd70664e5df3%不明1
221gemini-2.5-flash-preview-05-20_23K 2025-05-20config_70b15d89585c0474ed609606731f628680cc5e92125dc6211f8ee0e15d75da313%不明1
222o4-mini-2025-04-16_mediumconfig_12be17b71685704960c85bf890b38bb80c82fc559d8a65371cabe344713eb44a2%不明1
223gemini-2.5-flash-preview-05-20_1K 2025-05-20config_b88c9014976266b4f212f69ee24fc8135b020c4dc467645247f7a49a4b50d7d32%不明1
224gemini-2.5-flash-preview-05-20_8K 2025-05-20config_78175c7382e52d352f5969442a8a2e2d3ffc74f254418bd3581a9a8430b1dc582%不明1
225claude-sonnet-4-20250514_8K 2025-05-22config_d9406ffb2172cae3918fee69406912f50dd5e165d17bfde63f3e440fe6ef5f432%不明1
226deepseek-v4-flash-0731_none 2026-07-31config_79255a0c2c4909dc505f7c6ece0ebea2cf2794eb1cf644705d3ecca941fda7132%不明1
227deepseek-v4.1-flash-1017_none 2026-10-17config_b79faeeac43e5fa71ff90781da620b7cefa89319245ab58c1db2086b968288682%不明1
228o3-mini-2025-01-31_mediumconfig_9a56af7045290adb5d93b22d180332b8a018c1f49e1ccaa838952245b6f04b142%不明1
229o3-pro-2025-06-10_lowconfig_921267b4a6c1fd211fa55d009d4d1f80e18c0a43ac279977bda241dfd3bdb4f22%不明1
230o3-2025-04-16_lowconfig_a7347f7586623824fcfbee550645ebbf3bd718cd3895277ed1f4258983d15ea92%不明1
231gemini-2.5-flash-preview-05-20_16K 2025-05-20config_e944bb314bc85cf16d89362299fe4cb2cce537258def8b75d359a51bf6b158562%不明1
232gpt-5-2025-08-07_lowconfig_49cd7b6dd29f4a951f7f002d380544c00e3967c0a7b04fefffc82296ee8660c82%不明1
233gpt-5.4-nano-2026-03-17_mediumconfig_8cd4fae039455267739b311627202f690fa7f3b190f198f9d387b2006d60a85c2%不明1
234o3-pro-2025-06-10_mediumconfig_9c2091fbee4388af6494949c14989b24d0f566ec529584c75fed9c307c08839c2%不明1
235gpt-5.1-2025-11-13_lowconfig_f94010985602bf346a3cacdcd1932323dc66025544c4d829ee48f0165e0671ca2%不明1
236gemini-2.5-flash-preview-05-20 2025-05-20config_493a9334b881fd3024e2c897adfdc6c243cc4b0efc9b121d6e3ff025d0f8cebc2%不明1
237o4-mini-2025-04-16_lowconfig_8c5404b58c740ce12def212c866d68f2127623ae64c42474afbeb14288533b4c2%不明1
238claude-haiku-4-5-20251001_8K 2025-10-15config_b9f1e3d8df86d9008514b59dd514f75f309f951ec8dd7916cebdb3a7f28f2aea2%不明1
239gpt-5-mini-2025-08-07_minimalconfig_cc84af6b73a0a45c1189899de85f922f7b518dbca128d9c71c992b190447152e2%不明1
240gpt-6-sol_none 2026-09-22config_da4f7be3b8c02c4fdcb259211d2a3a452a0ebd84fec1882e1cab32f82dcea3982%不明1
241gpt-5.4-nano-2026-03-17_lowconfig_ca55e8624b335037a149f053d4a93546c554b08aa6775a0277f844cd6caaf1af2%不明1
242qwen3.8-27b_none 2026-08-14config_3478babdd8f1a6354758ea3cd85f98fc720288f6d9742eb5d456de52bede0ada2%不明1
243gemini-3.5-flash-lite_low 2026-07-21config_b42c41f4f380410f5bf637ebf4cbb85e1430c2ba814f0095db5d75a25565e6f22%不明1
244gemini-2.0-flash-001 2025-02-05config_94887e48cb18c726410b03af6dabf97b5f29cef52aeb2993f154c745e1d04a301%不明1
245DeepSeek-R1 2025-01-20config_d74cd9a37607d3ac1200bed74fc5dc886bdbd22d1d6161e3afdd333612e49fa81%不明1
246claude-sonnet-4-20250514 2025-05-22config_04179b1d64747c655e6913aee2fd00fe92961594ccf0dc6bc0c8771f7d26a1f71%不明1
247codex-mini-2025-05-16config_0b25bf009e9ea322fbbb8e5923e6b6d797df6618bcb6548626bc7e004d8a69711%不明1
248claude-opus-4-20250514 2025-05-22config_f9f88cc15855c3fb44c39a1529bdcacd2c3149ec887dd91df20c2281b964558b1%不明1
249deepseek-v4.1-flash_none 2026-09-09config_20bc8b65d6ba94f7e5cbc8c2dbe9400afc4f06cc571cadc377b2333bf935c1781%不明1
250gemini-3-flash-preview 2025-12-17config_7396e5a13b4db3c462349d7c290d5b8e5a5e4f02a49e3ef6640fd06122233df01%不明1
251claude-haiku-4-5-20251001 2025-10-15config_b3e281e03790711e2a573c7bddd7973a1e6f9d1222ec65404f979d799e17dacf1%不明1
252Qwen3-235B-A22B-Instruct-2507 2025-07-25config_ce972cd5f15d902cd5f765094e4a62564a2b8af2d6bbcf80da2d8353372a964b1%不明1
253claude-haiku-4-5-20251001_1K 2025-10-15config_d59222481dc96c1c6d66adf50715fab3a4b8cd4ca888dbf3c08b60ddfafff2581%不明1
254DeepSeek-R1-0528 2025-05-28config_ccbd70abd02ea5883edd80a9a07b91ffe61a47034632fb7e7a5720c334e5dff51%不明1
255gpt-5.4-mini-2026-03-17_lowconfig_ccea703bab3b79e6076986f186b999cad42b6c15484a02cfe871eb9f9648d0491%不明1
256claude-3-7-sonnet-20250219_8K 2025-02-24config_42142cdb60104f88181a29130275c3ef9c87efc2885217fa59cc8a37287fc6041%不明1
257gpt-5-nano-2025-08-07_mediumconfig_cc4e13214953afec486b85a688ac7564b70f1efc3f7d4a0b1a944665a42863771%不明1
258claude-sonnet-4-20250514_1K 2025-05-22config_6e07e672da56adce977550970c840a2a479cf0c00844cf0f4a9c1c09e376e6851%不明1
259gemini-3.5-flash-lite_minimal 2026-07-21config_67baccb6dbe8b9280a7ad42a586e244de688e83cd18753a792b973def8b37fdb1%不明1
260deepseek-v4-pro-0813_none 2026-08-13config_9fe26210de3e7cf88113d4e923303c1d379e22bbf161c2b30a7df410eb72a7d21%不明1
261gpt-5-mini-2025-08-07_lowconfig_2f9f2b48caa9aa3852aa338752d51bb9605e1b694fb8a11354d1832423cd7fc01%不明1
262gpt-5.2-2025-12-11_unknownconfig_5d063395d20addb02fbb14a3c4c41b6148635f98ba1ca357e17e41e88136809c1%不明1
263o1-mini-2024-09-12_unknownconfig_ec0ef473ebf9577f04ecad7b964706d6bcc275c8a49d93aec89bd31c756db34f1%不明1
264gemini-1.5-pro-002 2024-09-24config_7fb265845a6ce2c4071d5231dcc2877d7484be687d08eeeb2b3c13ab639c50f91%不明1
265gpt-4.5-preview-2025-02-27config_9c42b055dd14466abd0c399717449ba41a8ee0e9935c836493b2ba2afa847e8d1%不明1
266claude-3-7-sonnet-20250219_16K 2025-02-24config_2b29a9b2fb95eac499bd7bbf264713c9d2fc2118d278680b3bddbc9a8ab520711%不明1
267grok-3-mini_low 2025-06-24config_2ac0b32e8bdda73f7677785d26be48322bd6eec38f7f782a333bd70ba0123d4d0%不明1
268gpt-4.1-2025-04-14config_a67b333bc674bfeeac2ad9cdff758ec774b29ebecc747428d1181b8eff72b4400%不明1
269gpt-5.1-2025-11-13_noneconfig_e382a346f3d090b234f74a252bdb6e14d4f283b2611a811d1fe96bc85aa8f50d0%不明1
270claude-3-7-sonnet-20250219_1K 2025-02-24config_ce8c75462547a619952dbada44ac812f8c5287163eeab6832cce2cdee64115220%不明1
271gpt-5-nano-2025-08-07_minimalconfig_0b2a7b2e3e124567362865e78ce2c876f0f8076b2981f6cf39974b05b54af3180%不明1
272gpt-5-2025-08-07_minimalconfig_222260cf5ddf76d57f8d08955cbdfa2e59ca88089dbb893571f2c43afb99cd270%不明1
273gpt-5-nano-2025-08-07_lowconfig_30dd69b9382d205fd3dd389ab9c661c4a7a4f4ce044560db0ba39190ac431cf80%不明1
274magistral-small-2506 2025-06-10config_3a61469ee0a54275a91f3f9153201a3f7bfec4b7ea7d9e918b6d7837579d24bf0%不明1
275grok-3 2025-04-09config_4b42adcf3b8bebc79f3b3d10b2dfceb36d90919772412456858ff594a936b9b20%不明1
276gpt-4o-2024-11-20config_6a0af78239c86eb0dc079ff427a9971ae6b89e97e2b0b14c71fc9433f21e599b0%不明1
277o3-mini-2025-01-31_lowconfig_8e392b0161c315b6647a16f63f647ec489650a6ab3fc7913837a2edc1c8ac14c0%不明1
278gpt-4.1-nano-2025-04-14config_90373e62bf352e88e6921f48ea8575ae536b8511c43c400c5adde5f03540acd70%不明1
279gpt-6-luna_none 2026-09-22config_9bbb067aca89d4c3a1c0adc1f163031a21bcb4e23c9e1f42e47124654de0d0ff0%不明1
280gemini-2.5-pro-preview-06-05_1K 2025-06-05config_aa98e620fa2f433a8a72674259a48b6273e58ce86aa6ee15eab1e2223ca3b0100%不明1
281Llama-4-Scout-17B-16E-Instruct 2025-04-05config_b21d653692fee94a640375573b07132485c5da4479865700f91c67bed9cd893d0%不明1
282magistral-medium-2506 2025-06-10config_ba3f5ecfdcc32937d296f19dfe6ea9d0a3e82c6f4278272e0aafbb50c67574ea0%不明1
283gpt-4o-mini-2024-07-18config_bd5c1aae7478cf497ae867a3bbdd9467bb8d9b1bc4f8d920fcab87e842a371e70%不明1
284gpt-4.1-mini-2025-04-14config_c02e16ffc4d3bafffc1c036c0d61130dbf3e7946dbc87397b1d4616c8ce294d00%不明1
285Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e10%不明1
286inkling-small_none 2026-07-15config_d5e27515499b1bd4209e30a7d9e0494a9c93f1939ac2ed62e0d93edf7a71acb40%不明1
287claude-3-7-sonnet-20250219 2025-02-24config_e127eb3ecc2fb6196eea2e2d180e62211f2681bdb884219bf850b17e17b920cd0%不明1
288claude-opus-4-20250514_1K 2025-05-22config_fcad5192d98de10084bffb45101e775f983a62af6d2db526289c30ffc37927f40%不明1
289magistral-medium-2506 2025-06-10config_fe4a0f120ad12dc298baaeb937d87859915ade87275a835efee2a915c74037130%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

Humanity's Last Exam

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

RankConfigurationCapabilityUncertaintyFamilies
1gpt-6-astra_unknown 2026-09-03config_25d6b325a941c5563b85c85173810b4fbc64817a6e1f08a3d7df5096ce655bc955%不明1
2claude-fable-5-1_xhigh 2026-09-01config_f5f9bb4a158ecf32746eeb0a2871fcea455caebe04246ed1fa6e57fd5080d47347%不明1
3gemini-3.1-pro-preview 2026-02-19config_e68bb875be38122ac0497309d31ecb548a3be3bccac37c6db36492abc1b0f91146%不明1
4claude-sonnet-5-5_xhigh 2026-09-28config_821edb6ce30c930772de59be043ef6c390aeefdd14944641dc4bfb1e8047bd0146%不明1
5gemini-3.8-flash_unknown 2026-09-02config_d77e4f67317bfea831bec1e5698dcbba759262c5dd1c225db89a6faeaf1327a545%不明1
6gpt-5.4-pro-2026-03-05_unknownconfig_700974de20471b395adb62774cdc5e6088654864ea7cc4ffaad369c519699dfd44%不明1
7muse-spark 2026-04-08config_d44b10f0e691c37e7c14b057261d6a0b88129cab973e5a6904128f219f34f30e41%不明1
8gemini-3-pro-preview 2025-11-18config_39f5b0c0834e4eb701f5a68628426d42a419e026b082bf7115bc50f3e3d907b838%不明1
9gpt-5.4-2026-03-05_xhighconfig_660fe730ff9f38f55eaadd5bbe09f26f010a5fe899800cd59640a605d4bfa47e36%不明1
10claude-opus-4-7_unknown 2026-04-16config_64949aea5b4798bec1b323f0cfc6a0e91d1e00310b7b78a5a18e00b616e73cf936%不明1
11claude-opus-4-6_max 2026-02-05config_6973925ebcea60fa11b2f037b4359f8c4603e5f3037959da3c4d03c43f42596634%不明1
12gpt-5-pro-2025-10-06_unknown 2025-10-07config_59055441940a6bea9d63174a4af091e3c303a2ad55b1452719370a832bf7ba3f32%不明1
13claude-haiku-5-5_unknown 2026-10-07config_6a8b9071897e1b8cb893fc8c983916d2535710c82c09598e419fa00c0725de1a30%不明1
14gpt-5.2-2025-12-11_unknownconfig_d304de2673e41c09968a2334bfa1af5655fbac2907a522ab042f259df382d90a28%不明1
15gpt-5-2025-08-07_highconfig_69ecec6dacb41cc4f9c595637f81a8d34783313db732f1f343accdc4a69fe58e25%不明1
16gpt-5-2025-08-07_unknownconfig_cf7756eb36f169fe7b7f9ca49a79060216346709cd86c0d0fb293e5a9e257ed125%不明1
17claude-opus-4-5-20251101_unknown 2025-11-24config_fdb3a5ead63c23f6b3ac926f22faf563617a28316903e0191bf28cbac821cb3525%不明1
18kimi-k2.5 2026-01-27config_005459d229eaa2c83bc541c2ce7e8ac815663cce448d4b905c846bffbc058d1a24%不明1
19gpt-5.1-2025-11-13_unknownconfig_ab9c4f0fb10d5121fa55d0ca8aeb0dc7fa558aca12bfa1fe068bf59eb2592ddd24%不明1
20gemini-2.5-pro-preview-06-05 2025-06-05config_520cb904234e435ed0d291db57c61343bbd9cd47b40a1cc6fbc9ab3cde2b19c322%不明1
21o3-2025-04-16_highconfig_93e08c55882a962e28ab63ad269e729f3e294bd223dbc9b3bc26b74898baef7520%不明1
22gpt-5-mini-2025-08-07_unknownconfig_0873d593916fa6075904e237e0ca63995a6572e45ebdf6d3f89ee7ebcd6a9e2719%不明1
23o3-2025-04-16_mediumconfig_e383580877c10a76467bad15a4578fc2e2f463ad9b54ad8d3d2c698bce63fe8d19%不明1
24claude-opus-4-6 2026-02-05config_d53d33bc2c05b5b373c9434c391f6ceb0afdb4204aebb579f37fb30e59574bf319%不明1
25gemini-2.5-pro-exp-03-25 2025-03-25config_10a145fe7bf681ee6f54275e9f053cc8fbeda5757ccfee7c66d867863d8cbcbf18%不明1
26o4-mini-2025-04-16_highconfig_dbd9d87bb365dab644590f8e33640376ba43512e4c52b2bf4024be74f8fb61af18%不明1
27gemini-2.5-pro-preview-05-06 2025-05-06config_b0c2701b97c3c2f6c3f1dd40292e19e97fc1597aeae2313e85cb5c68ade98c5f18%不明1
28o4-mini-2025-04-16_mediumconfig_f99ef8ea288a6cde886ccd45cd6989c4b0fb4f1b61c929903f71535e10832b0514%不明1
29claude-opus-4-5-20251101_unknown 2025-11-24config_49bf5d7860fdda190d62820d07cbba06e0c870254e8e91ad2526a74ca8d47d0314%不明1
30claude-sonnet-4-5-20250929_unknown 2025-09-29config_096bfafd4d12e8a3a13f4573307d1e76076e2de7b33dfafd6d8a1a6a2566c6d214%不明1
31gemini-2.5-flash-preview-04-17 2025-04-17config_9d2efb708965c9c3c0fbc19a6db6375eac0b5a0e40afaceb182bf8cce9e1703f12%不明1
32claude-opus-4-1-20250805_unknown 2025-08-05config_7e3cbe876975ab6a32afe3ceb60e7ef90a318b7452c5909652230b8a23d0a31112%不明1
33gemini-2.5-flash-preview-05-20 2025-05-20config_bbbc2b70cea1dbc9c8a4d681bb4d0f359191437401c99b5166129e6a8504056211%不明1
34claude-opus-4-20250514_unknown 2025-05-22config_65bc4378cbe1be090c451ec383a83cab2270270489e704bded064e8126a0a42b11%不明1
35gemini-3.1-flash-lite 2026-03-03config_ffb3b8f054e094aaa4f2801bc7ecd1e11f97fb8a4cdc42090b617125bf40e34a9%不明1
36glm-4.5 2025-08-03config_f2aa2e4a3dd92a504bf35a92a3028939fc89530567c0c624e4ff10693ddb2b9e8%不明1
37o1-pro-2025-03-19config_9a17cfba04138c9382259270c442a16c728e1cf665f0d7f2195a6ea0e2bffa2e8%不明1
38GLM-4.5-Air 2025-07-20config_c11079f6736b79cb813ce772789434f3095c0cfd3891036e34f185f3c6331b3f8%不明1
39claude-3-7-sonnet-20250219_unknown 2025-02-24config_555c39c3172d3c7355c3b2d5ed97ae6ce93dcf7fe2c60de215a6266937ad18d58%不明1
40o1-2024-12-17_unknownconfig_d457f10e94f0bbc5302b2dc756f9c3a3b6c5ecf26fbb8833775cbeaa171e5e6c8%不明1
41claude-opus-4-1-20250805_unknown 2025-08-05config_534b97a421f480535aabf998cf9b61e0561e4144239115a271a759ba557ac4258%不明1
42claude-sonnet-4-20250514_unknown 2025-05-22config_3afb5081c41abb96aab5a2e55021857c819047dbe5d7da39dad8cd59ff5f63a68%不明1
43claude-sonnet-4-5-20250929_unknown 2025-09-29config_122a7fb34b784dea798bb0c1475d7c20c53b156499ae3856f83533b65e27a1a98%不明1
44gpt-5.1-2025-11-13_noneconfig_c799e3f9239d5edb2eedcde98bfc6420dba466b32ef931a09835053db036629e7%不明1
45claude-opus-4-20250514_unknown 2025-05-22config_ac589ae25a74f51f26a1547ce5feff400675777b07a00d3cffa77e6d5b03604a7%不明1
46gemini-2.0-flash-thinking-exp-01-21 2025-01-21config_38984fb90dcd226bb057e2f69279fd70306f0ff67aeb8f0377d0f0f75197759f7%不明1
47Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e16%不明1
48claude-sonnet-4-20250514_unknown 2025-05-22config_0a826345ca7ce71aec37325caa311d17728bc2b0a88a31a9dd465dc5ce57b96f6%不明1
49gpt-4.5-preview-2025-02-27config_82b0b596de11c8b2ebd692040e9fa1dbe1b5b5e387543063b09e9adf3642e7ce5%不明1
50gpt-4.1-2025-04-14config_a67b333bc674bfeeac2ad9cdff758ec774b29ebecc747428d1181b8eff72b4405%不明1
51gemini-1.5-pro-002 2024-09-24config_15a08c634ca88c673eaffac846c70e57ed4a4d6ad603aaf105ce54da21e9fbb25%不明1
52mistral-medium-2505 2025-05-07config_16aa593d4b9d123698a9910243824c241ce8990d08c579b9b49b93911060a8985%不明1
53amazon.nova-pro-v1:0 2024-12-03config_19a124f77431f7ba504b88a72e9903e275a98af44a9e1f423a1752ddbbf93f564%不明1
54claude-3-5-sonnet-20241022 2024-10-22config_e7c81cb1468bb68568b41a781b84c3d8d031855865936688ba8db46784dcbd6c4%不明1
55amazon.nova-lite-v1:0 2024-12-03config_a88cb2cee387b434a41ea8870d0836c9fba311a08dcf8a8ed38c4dfa7b8043744%不明1
56gpt-4o-2024-11-20config_9e4ddd087b6766c3fa7d7206d5d341b961d242105b347f69dbdb3a96612d10763%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 reasoning

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

RankConfigurationCapabilityUncertaintyFamilies
1kimi-k3 eqbench-creative-writing-v3:kimi-k3config_d66c6e07fedc532103cff26a3a24b654216470b82fa4599cbb46193cc807d689100%不明1
2grok-4.5 eqbench-creative-writing-v3:grok-4.5config_f6bc46fa147cb6f6b9a67207d6897da9312ec39c66ddfa53a122fcc220190b9e76%不明1
3qwen3.7-max 2026-05-19config_31d9cfe80b6e949fc3f2a8d30c9655b243d8f03f4243cbdcd2e271852aa4020551%不明1
4kimi-k2.7-code 2026-06-12config_60744ea1e7a29d77cbabcb1a95f52e174f0d596baf5b52657391d809e36c4e6947%不明1
5grok-build-0.1 2026-05-29config_22a107e3f9a2a93b4e0466b2196fdaeb6eb7e2fe864e7df301c890432f1338844%不明1
6qwen3.6-plus 2026-03-31config_ba187e15c28e9dcb5bf3c4a6c1ae54e87ed4e2d6c30dc01a778ccb48a17de5010%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。
Back to all kinds of work