Writing

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

Produce high-quality creative and long-form prose from an open prompt, judged on human-preference writing quality.

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
1Claude Opus 4.7100.0%2
2muse-spark-1.199.6%2
3Claude Opus 599.3%2
4Kimi K398.0%2
5GLM-5.397.8%2
6Claude Opus 4.897.7%2
7GPT-5.597.6%2
8Claude Opus 4.697.6%2
9Claude Opus 5.597.2%2
10GPT-5.497.0%2
11claude-sonnet-4-696.8%2
12Grok 4.796.3%2
13kimik2693.9%2
14Claude Opus 4.593.8%2
15Claude Sonnet 4.593.1%2
16gpt-5.3-chat92.5%2
17GPT-5.292.4%2
18qwen3827b91.5%2
19nvidianemotron3ultra550ba55bnvfp491.4%2
20glm5191.0%2
21o390.9%2
22glm590.7%2
23grok-4.590.6%2
24inkling90.1%2
25GLM-5.290.1%2
26Grok 4.20 Beta90.0%2
27Kimi K2.589.9%2
28DeepSeek-V4-Pro89.7%2
29gemini-3.5-flash-lite89.5%2
30gemini-3.1-pro-preview89.2%2
31deepseekv4flash89.0%2
32Claude Opus 489.0%2
33mimov25pro88.8%2
34glm53flash88.5%1
35mimov26pro88.5%1
36Claude Opus 4.187.8%1
37GPT-5.4 mini87.8%2
38qwen35397ba17b87.2%2
39minimaxm387.1%1
40GPT-5.186.8%1
41GPT-586.8%2
42mistralmedium3586.7%1
43minimaxm2786.2%1
44inklingsmall86.2%2
45Claude Sonnet 486.0%2
46Mistral Medium 3.185.8%2
47glm4785.4%2
48glm4684.8%2
49GPT-4.184.7%2
50Claude 3.7 Sonnet83.9%2
51glm4582.9%2
52Qwen3-235B-A22B-Thinking82.7%2
53minimaxm2582.5%2
54Grok 4.1 Fast82.4%2
55llama3370binstruct82.1%1
56GPT-4.5 Preview81.9%2
57llama370binstruct80.9%1
58gemma431bit80.5%1
59nvidianemotron35lightning30ba3bnvfp479.3%2
60GPT-5 mini79.2%2
61gemma327bit78.8%2
62gemma412bit78.6%1
63llama38binstruct78.5%1
64qwq32b77.9%2
65GPT-4.1 mini76.9%2
66glm47flash75.8%2
67Claude 3.5 Haiku74.8%2
68gemma312bit74.7%2
69gemma34bit71.2%2
70gptoss120b70.5%2
71GPT-4.1 nano69.3%2
72llama4maverick17b128einstruct67.7%2
73GPT-4o mini67.3%2
74llama4scout17b16einstruct65.4%2
75gemma29bit64.9%2
76llama3170binstruct64.4%2
77gptoss20b61.9%2
78Claude 3 Haiku61.8%2
79llama318binstruct59.8%2
80llama323binstruct55.3%2
81llama321binstruct43.5%2

アリーナシステム · 群衆によるペアワイズ比較

Exploratory - not a ranked winner yet
rg-writing-arena-system-crowd-pairwise-arena-system-v1

エクスプローラーのエビデンス

LMArena Instruction Following

単一の出典。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1Gemini 4 Carbon (High) 2026-10-28config_a7f27e99a2a2cccc7a3b486cb32684f96418ecafed7a2e9ae9cd6d14a45e7fbd100%不明1
2Gemini 4 Argon (High) 2026-10-28config_54b77b3b47d74f28cfd02329b1ac05bb70e452978382cf4b874078529f71c2ee100%不明1
3Claude Opus 5.5 (High) 2026-10-28config_f992f0de6b366bc0caf43f31e088793271a8f5fc5b13b0a2ce933b6f5adb0975100%不明1
4Claude Opus 4.6 (High) 2026-10-28config_77f5646cc0e47023c90dc457364001721890c3fa3d4003b9df1856d19bf745e298%不明1
5Claude Fable 5 (High) 2026-10-28config_f603f39b46490fcfe8dbd3299b18f1e92dd0c855ed289126d4c2a080ed56116497%不明1
6Claude Opus 4.7 (High) 2026-10-28config_a0aaad310fe761f841fdfa74daf55fd18f75b90024e3f01dc8e4cf6206bbc15396%不明1
7Claude Fable 5.1 (Max) 2026-10-28config_9da68023f4e237acd279fec66e71e35eb8bcd75f7ae5821d12339a60dc9bc2d096%不明1
8Muse Wonder (Max) 2026-10-28config_5151c9ef37290b59bd8c2c340a5bebf3b268d307484608da8db67f13829e0f9696%不明1
9Claude Opus 4.6 2026-10-28config_af9287458b652a73b10ea2f8c357ec15e35e9d50091c6205275fae585778145e96%不明1
10Claude Opus 5 (High) 2026-10-28config_f0744ef2c393e6ccb4902dc7283b0b82765465e393af920561c1fd3e97c93a2095%不明1
11Claude Opus 5 (Max) 2026-10-28config_fc7db992c8ab123e3a61d6326192f17640dd6a05250ee5f3ad74deb5aafc5b6795%不明1
12Claude Opus 4.7 2026-10-28config_ce30c57d98befa2713a7c3fcba3ba219afea760216625a8c8b8d78e79da25a3395%不明1
13Claude Opus 4.8 (High) 2026-10-28config_6688bf0f937b86305534a0850ae1fc0b68a046e1ae88e673885bb11a5e84b9ea95%不明1
14Gemini 3.8 Flash (High) 2026-10-28config_cb75577e4633bf6d2cd4de90688919893cfd52406de9eeba44e138a32c50340b95%不明1
15GPT-5.6 Sol (xHigh) 2026-10-28config_6cea6cbf50d40798e95478053a66e16a97804242a8b7292643d395a29022185d94%不明1
16Kimi K3 (Max) 2026-10-28config_bc30d24757a1ce932a18821c41c0c9b8405a1b16b19502a3a7409b9577e57d8c94%不明1
17Gemini 3.7 Flash (High) 2026-10-28config_da6b006531c6a4326b6d484006a300c9eed3c5abcc76618b913a9c05abc9dd2694%不明1
18Claude Sonnet 5.5 (xHigh) 2026-10-28config_03c2546990cc8d476491d62f006d34e0ece3c8d832503cd61e1f7d406389cc4f94%不明1
19GPT-6.1 Sol (Max) 2026-10-28config_5af741d6a0a14ed166f35733f2841a9334589039edf0e635df142f63384c827594%不明1
20Claude Opus 4.5 (High, 32K, 20251101) 2026-10-28config_7a1158564c417621125fa8eacab1157570671a227e51b46c6f30afdf2d21854893%不明1
21Muse Spark 1.3 (Max) 2026-10-28config_61ddfceebea7c63919512963178f9e43eabb28d34f2893782752890d88cecbb293%不明1
22Gemini 3.1 Pro Preview 2026-10-28config_3e142efdbc73c717f5432b011ecfac9f8eaf54476c92ee30a93db380689ebf2993%不明1
23GLM-5.3 (Max) 2026-10-28config_edb1e7855606f4ff759e4100d76007fb0d79fb41f335093c61d8c2979cf95b2393%不明1
24Claude Opus 4.8 2026-10-28config_324c11c5722b34685b6e465ea823d74823ddeb9e4387919f9bdb2f520861d14592%不明1
25GPT-5.5 (High) 2026-10-28config_795ccef55a011bf19f0f76651be02576d2aa5e7d6cfdbc0355c195bec54b923592%不明1
26DeepSeek-V4.1-Flash-20260910 (Max) 2026-10-28config_ef15da98d9885e229a0946efce64fc5b689b4cb6b00a902236734c02bea1c7ff92%不明1
27GPT-5.5 2026-10-28config_2152eb00fef73aef4ad6f5a8313aafefda2069c44aca8f3df49be098969d054592%不明1
28Qwen3.8-Max 2026-10-28config_85b511ed6f219e580a64e564fa5408e5342a0dabb7a757e5e21da8778e7f700992%不明1
29Muse Spark 1.2 (xHigh) 2026-10-28config_1f86814b40e44d1485ecd3ec88bdd1fefc4f0725539aa1af02bcf09aef2ba15792%不明1
30Claude Sonnet 4.6 2026-10-28config_1a35002cb8737c36ede84db06d7c15d41be9e2bff3bc76652508f2c683e6287a92%不明1
31GLM-5.3-Flash 2026-10-28config_5a1f6a2ccc79fc3ea12ceb14847fb8f535dd6503fc7035eda1d87517547a4b3992%不明1
32Claude Opus 4.5 (20251101) 2026-10-28config_b7eda17e78ef56f9507aed7d79459fb8fa3205dc5053305faedc95346f0bb46592%不明1
33Gemini 3.6 Flash (High) 2026-10-28config_c1f09b7b1f13a1189452847266c4670261b2899e88ab9a37ecf65009f06e6f6e92%不明1
34Gemini 3 Pro 2026-10-28config_15af9f96a922d14eff5f38e1c386708d28c1a2ab890b239b06c0dc8760b47b4c91%不明1
35Muse Spark 1.1 2026-10-28config_2f97217543342de60df6dcae30bf54659206c579b1da94ca2e573e0410effb4f91%不明1
36GPT-6 Astra (Max) 2026-10-28config_9a5f6daf313aa48a4437dcf3dad5636225b98e013cf9119ffdc3df5be4db97fa91%不明1
37MiMo-V2.6-Pro 2026-10-28config_1e284b7d32c4b7137e8f8d8f3966aacdc911b095e66eceed10d1fd87927b0c1f91%不明1
38GPT-5.4 (High) 2026-10-28config_bf1cd453c68227fdfdceae7b82b36d2cfe439a87df2bf6d5f174cae73bd59f4091%不明1
39GLM-5.2 (Max) 2026-10-28config_b8f5d545f65c76069fc8cabeb04a46fac87eb2db87bdd45ca332c19d9d1fe7f091%不明1
40MiMo-V2.5-Pro 2026-10-28config_d8c4d7bde189597ff4285c14421be680ce51874cac7182cd9a71931efe91a57091%不明1
41Qwen3.5-Max-Preview 2026-10-28config_0d6bcdc4b68ce58f2fb206211eeae0e5aa73c58ea7f378dea62dcb38a589b26d91%不明1
42Claude Sonnet 5 (High) 2026-10-28config_7bd44f4a6b5ecc02ae45753361a784fc63cdb997227b23985fdf793d10c528c691%不明1
43Gemini 3.5 Flash (Medium) 2026-10-28config_0f70da84924f02400ef94a84493bdbf783ed7a8ab3c1deddedfccaab03ae085191%不明1
44Gemini 3.5 Flash (High) 2026-10-28config_0188113902d4be032fbb0bc3f5b8ba150bfcc9abc4ba231aeee91c7c52b9516590%不明1
45Qwen3.7-Max-Preview 2026-10-28config_b054bbeae25520e1426c5248c73e80d3d628bc97c2293a45f32df5fa45ffc36a90%不明1
46Muse Spark 2026-10-28config_0a6df124a4c6b58f5323b06e209f6ff52c4d83187ed06d31b9a9c0d798f6bbe990%不明1
47Claude Sonnet 4.5 (High, 32K, 20250929) 2026-10-28config_0e1a19bbb642fbb9cb122b728998a39b26cb5fac89b077d96c6b4e29be71459790%不明1
48GPT-5.6 Terra (xHigh) 2026-10-28config_71f9326707ed28cdd757694cf9c170a128f261057e17c10735981eaef4870ca490%不明1
49Claude Sonnet 4.5 (20250929) 2026-10-28config_d4cfae464d93f71fcc6e68d9c3c00019d54553df87958aa9140ab78eac9f3efd90%不明1
50GLM-5.1 2026-10-28config_3e90f1ee0c2f80cc47386cce8530424138786978de3b0f62a7d89e1ced70ee8690%不明1
51DeepSeek-V4-Pro (High, 20260813) 2026-10-28config_285b5ec61d89d404dc2b44dc8bbb863fbd0690f839e18054f20caacba9b2066490%不明1
52Grok 4.5 2026-10-28config_194cc086c069cce46c6c448461ba399a0d22b590608e1242e5c09c989ca2ea2d90%不明1
53GPT-5.4 2026-10-28config_9d6e5deb34e945dfcaeda25df4c23cd736a2a0ab377a0b696efa9e54b51ff21a90%不明1
54Claude Opus 4.1 (Thinking 16K, 20250805) 2026-10-28config_759de269af94bac41554c69dc47fdb97324da4ceaaf5ce8257a29314efa1365889%不明1
55Gemini 3 Flash 2026-10-28config_9e6f740aed0205bdeed46e6f1b72dc531bfb2382b2f50dd2e3be4eecc85ea0d089%不明1
56GPT-5.2 Chat (20260210) 2026-10-28config_14bc4f2617d9ad5d059ad9820f4cd1e37fedf13a98ee59cbcb633dfe711138c089%不明1
57Kimi K2.6 2026-10-28config_d9668596f8f48cac6a1902cd6b4b49562e678ebdf0c1a2b1111fead1e18fe0be89%不明1
58GPT-5.5 Instant 2026-10-28config_0193caaa699091931bbea5677ec384bd05d858fb60880529340a1591511263fb89%不明1
59Claude Opus 4.1 (20250805) 2026-10-28config_1523e283027c4561a9b835201e964273865b1858ca120fb8919cb5a34232cf2d89%不明1
60Gemma 4 31B 2026-10-28config_8971e480b29bdcd78425097cdebd0c87d3da59e5175dc29972000c89d01e8f6689%不明1
61DeepSeek-V4-Pro 2026-10-28config_1c570fedf0c7c706ae0b14b79e45562c00cd07dd9283c7fad2f37d8eaebf272488%不明1
62ERNIE 5.1 2026-10-28config_8e59d41d35a9e2e9ce4202e170b3c1342c27638d0c21eca75b126a117d50e3b788%不明1
63Qwen3.6-Max-Preview 2026-10-28config_4f3cc6df32a1d8805f8553de4c73cd9ba382ab5de1260af6d7bd4bef8822258e88%不明1
64Grok 4.6 (High) 2026-10-28config_c13b8be1ae6c822a9542e431d634c5779c03285fadf7f9cf34ce6ec749ec350b88%不明1
65GPT-5.1 (High) 2026-10-28config_7a7fb1fd10198c14a324cfdd06b665c0779c51f397fe87a610b8b1ddc01ce6bd88%不明1
66Grok 4.20 Beta 1 2026-10-28config_e5c7089af1fbd3833fbd7bc047b937e1de0517e24b2c1ad4c39ed2256cdd749388%不明1
67Hy3 2026-10-28config_fb4b03b57dfd3849e4df0c08ba841d2e639f74a7c4c0db468e71de0abeb098a488%不明1
68GPT-6 Sol (Max) 2026-10-28config_c38cb542362d62953fef0b86181989eb17819fb195e3293e51bcbd7fb499d85b88%不明1
69DeepSeek-V4-Pro Preview (High) 2026-10-28config_2bcdef8c23dd525630d65caba94237e0119de558ab0f500f27d2e9d55a6d561d88%不明1
70Grok 4.20 Beta (Reasoning, 0309) 2026-10-28config_9836176c698cfc8a92b37e6a21bf857153c155a4a06e71057237772789000a2687%不明1
71Qwen3.7-Plus 2026-10-28config_e0e59bb58043a11706cc02ff5079ce50a3a3546cc2623bb1afe86de792a3916687%不明1
72GLM-5 2026-10-28config_191641adf33a0e232b191177057f899f1d5421ec2964068a13ccef7e8e166ddc87%不明1
73Step 5 Preview 2026-10-28config_4ff984efa6a6dafb8a53314c0c9e16390ed4bfedf752e214d1d8abb63dda616e87%不明1
74MiMo-V2-Pro 2026-10-28config_fa96d8e6a54b9853f1ab0e23b66896001f43941ac15bd716df6910dc1b776a4e87%不明1
75Claude Opus 4 (Thinking 16K, 20250514) 2026-10-28config_fbaf87661c6af64a60a02307e799ad5d9d39f0f803653284da5023eaf421e37f87%不明1
76Grok 4.20 Multi-Agent Beta (0309) 2026-10-28config_43e9b92a78c657531f3e3029c8dcf0a50dece591149be65b7ab06e5092b9e0c887%不明1
77GPT-5.6 Luna (xHigh) 2026-10-28config_a197468c44d845af9ee569d8d5bbaa0aea364eb1f46cb77824fb115c6f0afa2e87%不明1
78Gemini 3.5 Flash-Lite 2026-10-28config_fc1abc3ca282c938aabe4a53b87dc816d7b7218f7cf81b16d61a519d9f9c7c1387%不明1
79Gemini 3 Flash (Minimal) 2026-10-28config_8056a22c2f7a5bd82ddf386f2c9f6bbee588c419edee3150fad5964bdd4cc7bf87%不明1
80Beam 1.0 501B A23B 2026-10-28config_efe719be9bb5ddbbfc5636582db2b2421bb4aed8b39bdbac700026bbfd6a801a86%不明1
81Kimi K2.5 (Thinking) 2026-10-28config_40cc18f2be11653660fd5ee05b217e986e3a4857719c7686c6133f156bb983c086%不明1
82Gemini 2.5 Pro 2026-10-28config_e342ddfac5a30c81cbe8e9cc5a921b0738d4952386e6320e6d8d80266fd651a386%不明1
83GPT-6 Luna (Max) 2026-10-28config_bfa11f72e621217b574e612e354ab2caf6abf1586048abeb9adf74269111ba7e86%不明1
84MiMo-V2.6-Flash 2026-10-28config_6b2a2a1b2de375b0081506eddcebabcdb30c030b3bfb0deddf720c1213af802886%不明1
85Grok 4.7 (xHigh) 2026-10-28config_c96f03fa7d29770132d40add25f3c0a7c07815f696ae4efeb143cf21f5fe2d7286%不明1
86Gemma 4 26B A4B 2026-10-28config_fe7037f0f0273c44122b6581a7dbd05d7d0eae7eb9a80f8bf45dc88bbb3af5d486%不明1
87GPT-4.5 Preview (2025-02-27) 2026-10-28config_882189979edfecf5bf5c98d220441537907c5e7982831ca261fc038cc49b805686%不明1
88GPT-5.3 Chat 2026-10-28config_81dc2a9d477e72aed60a8ccb4827e7979bf1b81c4df6ed89580938a5d0cb9a5986%不明1
89Qwen3.6-Plus 2026-10-28config_7430ec15fe6eebe2d84f8628ff7fd07e09d581e67aed46e4d6a89b5c54f7c40c85%不明1
90Dola Seed 2.0 Pro 2026-10-28config_258c54ecb2053808fdefe64a8a3ec4da7ff06be6f166c66b867c2da085203b0785%不明1
91GPT-5.4 mini (High) 2026-10-28config_0d3ada7750f1c5dfdbd37f4c965313f89ae23b399cce4a7b6712f78a702c07b185%不明1
92DeepSeek-V4-Flash Preview (High) 2026-10-28config_e032cac84b89bd9eb1439cc3b84c7d74d35e818a03ba28c6a2f884b8a78f9b9185%不明1
93Qwen3.5-397B-A17B 2026-10-28config_baea1404b72b29482fcb619b911d01c6c9ea7a54a33ac33195a257b7108e5fcf85%不明1
94MiniMax-M3 2026-10-28config_cc4f895f1ee69e5ff20cdc9b3c9312055877df851d0dd64b864606cf57fb1db885%不明1
95Kimi K2.5 (Instant) 2026-10-28config_8a281e2875fd206f80a617fbc9335acab9a32ab61bf424b4d7b341ea8ac94fe885%不明1
96MiMo-V2.5 2026-10-28config_5f92c3c7a5985bae1c556be92756f9690c5813d48e48b863f3dc1e313222a7d385%不明1
97Grok 4.1 2026-10-28config_0ff72123938642b945a2742ec425a3a4db93abe55db7f39e3bab73f8ea6c9f2f85%不明1
98Claude Haiku 5.5 (High) 2026-10-28config_d6980f950c2651c24024a05c2660ba602be5c4eac851e3bf79eeb0c22b8b8ec985%不明1
99Grok 4.1 (Thinking) 2026-10-28config_e7058908166f1a1c6919121ca185b7e439fe0c927098e45d93a9b4e55b6de9fc84%不明1
100DeepSeek-V4-Flash 2026-10-28config_0bca2c350c6b9d11fbeca654882e27bae1efb818ff54f26212e00d7371084af484%不明1
101MiMo-V2-Omni 2026-10-28config_9dcd3925379342e348775e114caabe73569166c8692ceafe5461c1db47a8172384%不明1
102GPT-5.2 (High) 2026-10-28config_5fefb900c9b16c06204945f774d0e77d466cd63f372419bda1a4c310ec87296e84%不明1
103ChatGPT-4o Latest (20250326) 2026-10-28config_f4ea619df3a0c70ce6827e63a65eb1fbca062d6a432bc1405758f2a55441c97984%不明1
104GPT-5.1 2026-10-28config_7b73c354105b7c6ff264c6adfa5633f95f59e0cfdecff5de75d2e817852df64684%不明1
105GLM-4.7 2026-10-28config_3cdeac89880efd10759c7f7745163d6e11253e2da08fbf29ff19115a1a6b94b684%不明1
106Inkling 2026-10-28config_f7c1272807c4450fa8759b7cfa16997ecac5f3a01f497963134a91b73354f78184%不明1
107ERNIE 5.0 (0110) 2026-10-28config_e0f49edc6629c9fe5668a94287d89b17aaeff3fd6908ef06cc5f06798f1ec54484%不明1
108Qwen3-Max-Preview 2026-10-28config_1cc84be88cce155e85190fe9badac7538d827f56c5a64d80ed4401843921039a84%不明1
109GPT-5.2 2026-10-28config_a1ca56cd4024de98dff6324f1f80b6daf379df05f3d76e11a4100d93b2cdfc4a84%不明1
110GLM-5V-Turbo 2026-10-28config_c78c296952b5fc9ad01d922654468b90bf366c711dfdddce8c8ddd90785f47ba84%不明1
111Qwen3.8-27B 2026-10-28config_967271e0779bc49acb9666f1c290353d38f8d622807c9c6eeeabdb60e3cdadf683%不明1
112Mistral Medium 3.5 2026-10-28config_bed2f405a786663b4f4ba02bef1fd34955258a5e7b6ca84aa6ab2704cbff823183%不明1
113Mistral Large 4 2026-10-28config_ca562e451360b954eaf1d010dee192b2c89ebcdc7bcf862ce38c9613b593d0d483%不明1
114DeepSeek-V3.2 2026-10-28config_498de9dfde41b45d0926761be51e8c7c00902d9271c23be871f9e59f1f92c9dc83%不明1
115DeepSeek-V3.2 (Thinking) 2026-10-28config_2c1c5aaefecc339dcdfa46cf4fe210ac93b0dad37cd0df55129830a5617e0f8083%不明1
116ERNIE-5.0-Preview (1203) 2026-10-28config_1dcc7251e449ebfbcf78d3a0a0e1388a62761d8c596a379632a7ee279db9c0aa83%不明1
117DeepSeek-V3.1-Terminus (Thinking) 2026-10-28config_685531e9f31481918b7161023e0220803450079b192004ffc10d1c0efaaf9da883%不明1
118Kimi K2 Thinking Turbo 2026-10-28config_5c28f77f9a132d9c951b9ed88d4cbd0d458baee6e8ec1073c28f75d19086c67683%不明1
119DeepSeek-V3.1 (Thinking) 2026-10-28config_bd27beb5362b2b0f62c6f26e8a0c15e703fd0ce143ede2352971be5abc8a64d782%不明1
120LongCat-Flash-Chat Exp (2602) 2026-10-28config_09b3b7fe7f7d65deaff789692fc750e5f9dbfa225aa03d7abba604473aac304f82%不明1
121Claude Sonnet 4 (Thinking 32K, 20250514) 2026-10-28config_a2e308657128de01ded419128cd12831bc90bb9036a46418dbb7fafe8ceb593a82%不明1
122DeepSeek-V3.2-Exp (Thinking) 2026-10-28config_5673c3091be6c3ab2f68144cc7e5ae5733242eebecdf7561259ad93ab3cdbd9d82%不明1
123Claude Haiku 4.5 (20251001) 2026-10-28config_fe36ce3cfe3a5577b457773687965d6113d9525c053ca0ba02b73bfc3f7447d382%不明1
124amazon-nova-experimental-chat (26-02-10) 2026-10-28config_213a14f054d6902b02f6f49e386759f8a1c24342c6ddae6dfdd93d0b874402e082%不明1
125GPT-5 Chat 2026-10-28config_0a57e4586120a824bdb2c62507dd14a42f83acf61fbadbbc9329ae7fae94c00782%不明1
126Claude Opus 4 (20250514) 2026-10-28config_7dc35bf7547f6255602e2f2a7b8dd8c67c85053f7c5ffb52fd2c80172e00c43382%不明1
127Grok 4.3 2026-10-28config_f1e7a96723ba338b1aeed2be14134c610736403feea66da65db9404e472fa35d82%不明1
128Muse Glimmer 2026-10-28config_26af2761ba304815b7d7aad05953e932d2616c0a12aec04688648ba83430cba582%不明1
129Qwen3-235B-A22B-Instruct (2507) 2026-10-28config_31445b6420ed51f301075ac8c574526d3cbc482fa3c69197b3802fb5e768a0ca82%不明1
130DeepSeek-V3.2-Exp 2026-10-28config_fab17572e418897b936b78b49a8a0d23198512affec21e4a904ab5c79530f0f382%不明1
131Qwen3-Max (2025-09-23) 2026-10-28config_bb0b4e157a6c4d8bcd678083e9643d4f049e045925c724dbc99dbdc41749b15482%不明1
132GLM-4.6 2026-10-28config_fc553cb51b47b631541100b29d32f130641b55ce613063eee8a2db890b17fbe382%不明1
133Claude 3.7 Sonnet (Thinking 32K, 20250219) 2026-10-28config_e73f6faec4ee1179a8605460ad37937e426795c3fc672d960366cb1d6544125882%不明1
134GPT-5 (High) 2026-10-28config_268a62731811a21bc5534e5a434b24652e2af82554d578bb536ca078f39da14981%不明1
135NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) 2026-10-28config_5b5868869b9d198d20292b355fa2ebffe386c8ec7bce0b3492854f64894a079e81%不明1
136Qwen3-VL-235B-A22B-Instruct 2026-10-28config_1201020d37023ea30c6296cba5f81ce3a31a1088f37740cc22d8595b842c199981%不明1
137MiniMax-M2.7 2026-10-28config_138a732d9f9931d8db35e65a3f7aa0cad50a4ffc4fe8a83b0d40a57b2914af7281%不明1
138Gemini 3.1 Flash-Lite Preview 2026-10-28config_681be1ab222d77e3a104b588d542e3b5a0874a51fb94cee53b0336d44f4aefa181%不明1
139o1 (2024-12-17) 2026-10-28config_1207dba4ee41286eda9861cdad2e5683cff2f54b57e9b971fd09ba4e7ad2622a81%不明1
140Qwen3.5-122B-A10B 2026-10-28config_0e78a447205faea460ba13c028e24fda45a31e9583a0bb11a1ee30f6934f232b81%不明1
141NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) 2026-10-28config_dd1800e68f91f3d0566ce0fc2fea9a682f0c9c3c66c2e5fd095fa0df836d4a3181%不明1
142GLM-4.5 2026-10-28config_20cad6a70b22355373304ad0d2c55a315c9310bba836ffbc420f4e21885adb6180%不明1
143GPT-4.1 (2025-04-14) 2026-10-28config_c64f2c4e55a3760839f3fcaf315934683da6e7115eebc66145f9df589501c99580%不明1
144Grok 3 Preview (02-24) 2026-10-28config_b39dc1035d9fe9f153fc886bc4b688da7a8941ec2e3b3565598ef46a2c4a124280%不明1
145o3 (2025-04-16) 2026-10-28config_7d0c4016da9a3cf6533bcdb71e6c485f293a14ab0e2d8e4c52c563c7389cf54180%不明1
146Mistral Large 3 2026-10-28config_a18710ee6c4c70e43284a24f13964adf807e4bac7db4d75102856413e8d6cd5280%不明1
147DeepSeek-V3.1 2026-10-28config_e143a3c721c7d3318773d86dea5bcd12c19ff93fad7ff623808e970442c3163680%不明1
148Grok 4.1 Fast (Reasoning) 2026-10-28config_666cc17ee7439a64c93dfa16fc85f05e47a71e9a37eb60cf8e45cb465c96e65a80%不明1
149Qwen3.5-27B 2026-10-28config_1955d7921589746a123e5fe804f50f995a2c51cb1c44f4fc38aafc96942dac3480%不明1
150Gemini 2.5 Flash Preview (09-2025) 2026-10-28config_139dc8072893c113a817961d5970effeaaa3ec24e1e8fa129dfa9c9320b77bcf80%不明1
151Gemini 2.5 Flash 2026-10-28config_61cf2339bf233dbf1136df7fe2222e20fa7b5accb413702a9442bbcc3520d3bc80%不明1
152amazon-nova-experimental-chat (26-01-10) 2026-10-28config_3f12119f15fca26c04d999a2b9e01b0393bde50d149610d13b9e17bac315dd3279%不明1
153DeepSeek-R1 2026-10-28config_30f2960475e1b1d85c84f7592d0dbefe5d8debf10db845aa4f886f709621860479%不明1
154ERNIE-5.0-Preview (1022) 2026-10-28config_71a8d6feb59ef9709fe437fef80b9cc64ec63e367e81bee5edc7550961b01a4179%不明1
155Grok 4 (0709) 2026-10-28config_336fe847175934fc25e7d49a5bb4ed1b3d19c80966e8567f2699fdac1d120e8779%不明1
156Claude Sonnet 4 (20250514) 2026-10-28config_278dc9d90e8b44f4ed91e65174022b51f42e371a65f00cdb6ed8ba8ae4cf93c979%不明1
157Hunyuan Vision 1.5 Thinking 2026-10-28config_767b77c6e5ad89705d80b0c82b1defbe5abf8bd15af907e37f4e7ccd84839bb079%不明1
158Inkling-Small 2026-10-28config_893a28201f6d03b946248701d46374c5c08f5996cfab413136069b1482f44f2279%不明1
159Hy3 preview 2026-10-28config_da881bc5930957d17687f2a45b49315452cdb02be4f2f9d757be66d67efb331a79%不明1
160Grok 4 Fast (Non-Reasoning) 2026-10-28config_4018d6fc16b0cb77ebee11288e9dce5001069fcedfaf899e2371b8d82552f9ed79%不明1
161Mistral Medium 3.1 (2508) 2026-10-28config_0eb4cac4e6967ff44169f0ec2b1e9ebe93e32f455adbd2135d2fbe7a7de9a79b79%不明1
162DeepSeek-V3.1-Terminus 2026-10-28config_dc56c6efb2b4c90fbd7d358b83c2180ac198358de7bcd5b6144aaca5bc63a96479%不明1
163DeepSeek-R1 (0528) 2026-10-28config_d5f8fb65168666ef2b322c724cb7b2cd729a1f634374d3ef139958a51026a93578%不明1
164Kimi K2 Preview (0905) 2026-10-28config_e2f7f480f9e1d2c43dd60fa66fe0afe22bde6136879c765092bec118e56ab50378%不明1
165Grok 4 Fast (Reasoning) 2026-10-28config_64aa7bccb1a9e8ab77c82f7ebdf154c5f32e482e46a61228bc61f12422c63c5578%不明1
166LongCat-Flash-Chat 2026-10-28config_138037edd8573a3cb4a5ef73349a4f24f289adb990e327689471b60cf76c6ece78%不明1
167GPT-5.4 nano (High) 2026-10-28config_3ab42abf173a760e5318b74ffc0db80e751034de8993ee9f119a9006cf3fcc6d78%不明1
168Qwen3.5-35B-A3B 2026-10-28config_916595b2490b60e0590e8de94402c61ffd8f83b54eabc1e9a13a2ee7ee1acff878%不明1
169Qwen3-235B-A22B-Thinking (2507) 2026-10-28config_d0c0decc63fb32058ce6d263db5d0f90a6710d8da27cd6e1646b543bf1096c8a77%不明1
170MiniMax-M2.1 Preview 2026-10-28config_bb1577ff1028cac7bc31235c314413fc291a3088a2d8e421f29914f296842b2477%不明1
171Claude 3.7 Sonnet (20250219) 2026-10-28config_969de8d3ebdecbe5d1ae3ce0e315c3b0b837303646516f8f268c488e0398796777%不明1
172Step-3.5-Flash 2026-10-28config_cb35a09750218550ce8fddf71fcf9138ed6495905f2f022c1c2552926399413977%不明1
173Qwen3-Coder-480B-A35B-Instruct 2026-10-28config_fba22cd76ad43ebf0e3c19f55f7f771d81e66d161cacba0d8bcbf178e08335cb77%不明1
174Qwen3-VL-235B-A22B-Thinking 2026-10-28config_a229d83b798aa9d9345407cd33ed0cfdf3e778d72cb2f988c1d652e3ce7cec6477%不明1
175MiMo-V2-Flash (Non-Thinking) 2026-10-28config_71ac2b0e48d52347740e3be031cc4d7b97dbf16ee404fb8805afc9fd14eca8e377%不明1
176Qwen3.5-Flash 2026-10-28config_c06297b4fedb48fc74e067fbde3e2001165f5c083da7e8da19c4bc4895cdb36277%不明1
177MiniMax-M2.5 2026-10-28config_076cac0c4c906cc631b960f175bdf5977b6d8de7b23bdcb3a4394c3ec3cd3e0977%不明1
178o1-preview 2026-10-28config_8b9e86c8a6376b5eb70eb5bfce4ce7b3ccb2433c8d22e95cbbc352734d0e952377%不明1
179Kimi K2 Preview (0711) 2026-10-28config_f333a72c2c2e4c9f6dcb36fc71e054c89a5137d271d372ea983244e9c4b4aa0177%不明1
180Qwen3-235B-A22B (Non-Thinking) 2026-10-28config_0255ff37e733246a8759b42b9e421a52c0f5ceb4c7bf13d47ddbb1f24a2b6b2977%不明1
181DeepSeek-V3 (0324) 2026-10-28config_9be09908d3996fd154a7b00026822e2f93b80af77604e00b039e7c782b96fc1676%不明1
182Solar Pro 4 2026-10-28config_ae28bef4e38fb7ba5ab0b5b28e245f2740cb135c4c2a32204c2a16b3d124fdb676%不明1
183amazon-nova-experimental-chat (12-10) 2026-10-28config_83d69c562b06bc55c4e8e745832abcdd2f28083eb1fb2b605dbe9d4d73cf2d3d76%不明1
184Qwen3-Next-80B-A3B-Instruct 2026-10-28config_10219ca0cf771c8e086fab1e5f5c0fa90afab703a8904075645220fcaba4346276%不明1
185MiMo-V2-Flash (Thinking) 2026-10-28config_1055d6c8047e3dc86621439214ffab66dc2835f2483cd1f017a16abc551a2cd076%不明1
186Hunyuan T1 (20250711) 2026-10-28config_d9f64e3ef8d455d533bd39e312b1049d38425297f595dfa759771499aacc29bf75%不明1
187Claude 3.5 Sonnet (20241022) 2026-10-28config_c0c97712383a593923bf3cb2fb2d791da35b0a84833dd432adfd89cc4e7fb98c75%不明1
188GPT-4.1 mini (2025-04-14) 2026-10-28config_51814f5eb2104fe16b69aeab7e180f27e7a197a3f836580e6a021f455b297e7375%不明1
189GPT-5 mini (High) 2026-10-28config_0a96f6082bdfebcf8c2c2130c0ff06af050bdb526c824ab0fd2ffb336b3d621375%不明1
190Trinity Large Preview 2026-10-28config_4cfb8ffdc858ccede9bc781715bd2245184541edae957db27309c44520f7771b75%不明1
191Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) 2026-10-28config_267ca415ff529ac542589bcd0064e3e10f68abf8afbccdd7370114e2b2b9614175%不明1
192o4-mini (2025-04-16) 2026-10-28config_9eec79eb14477c399df476d959f7d4bbcdefd56f523b98ff72659501b78f572975%不明1
193GLM-4.6V 2026-10-28config_0bc12caf6ead525cabc8ce3ca1dd2addf32c86464d089ee4710e9edac6cb2fe674%不明1
194o3-mini (High) 2026-10-28config_f1c5661e1102cc4c479e5e0ca3068586f738e4317b1599c16c0b6edf4457b7ad74%不明1
195Qwen3-30B-A3B-Instruct (2507) 2026-10-28config_73275d0ab03943ad3359b9566fb4cd6b748705d05b2cdd5271ff6355c75de7d474%不明1
196Mistral Medium 3 (2505) 2026-10-28config_bcf15f3fe11558fb540a7895e996ee83b2408aeafec388b2ea992016857b45ff74%不明1
197Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025) 2026-10-28config_d67d3e57f1e94903e8642011d564e095f6d50dd92ecf2775ac753af378d5283f74%不明1
198GLM-4.5-Air 2026-10-28config_cde3e61e085608ed82dba351a3dde92daf286d1e1d58fde8495e9123c9b321da73%不明1
199Grok 3 Mini (High) 2026-10-28config_e16f52b5404b2c045ffe158b97ca97b04118da40581783f10f7d326191451f2473%不明1
200amazon-nova-experimental-chat (11-10) 2026-10-28config_35930ce356194e10b5f7c5db872ecb8ba0772589662eab4bab6c1b0d95fb1ba673%不明1
201Trinity Large Thinking 2026-10-28config_9e8fc79c1e7a49312e5e772cac19dfc3aedb0d8d3fdaaa13773747afe30cbadb73%不明1
202Qwen3-Next-80B-A3B-Thinking 2026-10-28config_23b768b56e8f13a65be6271533dadcba1a9d29c4347409d483d4aec26c369f9573%不明1
203Qwen3-235B-A22B 2026-10-28config_6c9bccd4acebe4bc651c1ecd6f6553fbdd285c5ade48f9c00510c015956004b773%不明1
204Qwen2.5-Max 2026-10-28config_15daea73a19d5818caa5e4e2a02051ff7dba249a9ca1c4282e4db2367b1ec07c73%不明1
205Hunyuan TurboS (20250416) 2026-10-28config_f6d0d2c415c44417a0286938f78d0dfda940ef66f6feb630cac9f9975460166672%不明1
206Grok 3 Mini Beta 2026-10-28config_e2e6eaffdf3563a008b306be5848dd2e79bac1d21af171bc276c0553db0cac9372%不明1
207Llama 3.1 Nemotron Ultra 253B v1 2026-10-28config_1f7f5c70fd7deffe29c9ec01c384a6af3ad2543dad40757acec275856e8303ef72%不明1
208Hunyuan TurboS (20250226) 2026-10-28config_d8e022e81681608b76292c90cbbf6211fc4ac0b9e3dd39b0e8b6b15f9c4b875272%不明1
209GLM-4.7-Flash 2026-10-28config_7ef80bc3bd6f42904a69d51ee471a8f95d98c076336c777372fa127c3db30a1971%不明1
210Gemini 2.0 Flash (001) 2026-10-28config_d1b1b0db00b56ef7cbb36ae8f7264af40af250b2076353e942b5fcf4ba9fd28471%不明1
211NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4) 2026-10-28config_60a65e97eefe74b0fb2384cc7fc309104784dd0cd3e72668e0fee702a0e6974e71%不明1
212MiniMax-M1 2026-10-28config_a8c3bf00da4b0f6c19ac84ee9569719aecd9625a6726c7d638893ad9783ad47071%不明1
213amazon-nova-experimental-chat (10-20) 2026-10-28config_14c2a5700725906dab6c884cc20d8c9e0d4cf247832614530937574c32fe6b2071%不明1
214Step-3 2026-10-28config_5fbe3da681734fdf3ab2a312d3939799155a3404d4216247dfaabe3c7a0020e771%不明1
215o3-mini 2026-10-28config_51dc510b6014e72ef3a2fad601006b48fc90644e48728ce983a5992f220674c371%不明1
216Gemma 3 27B IT 2026-10-28config_b671f3cd5d7cb4718e0cb573edce4667c167301eee92d1a74d9f2f939e8152e570%不明1
217DeepSeek-V3 2026-10-28config_7046745074909a8f9a4244c49d2ae7cc937818d455fe187d1c3edfbb15ec71d970%不明1
218NVIDIA-Nemotron-3-Super-120B-A12B 2026-10-28config_6df7714740bd7724981a3e01af1fbe7c4eec7c096f05ad450098ce3c959fc9f070%不明1
219Command A (03-2025) 2026-10-28config_4e6a6283660bd02c03de213a04f5703b676dcc66b7feafc288dc673c247c192670%不明1
220Gemini 1.5 Pro (002) 2026-10-28config_5724d5eb418aa78ea117d8031f70c83b7eec77220ae5e6d4f2732eb267fbced070%不明1
221Granite 4.2 30B 2026-10-28config_b39c4dac649f679f038fab9cad47e3559d80d35f223c9ece331858445b9fa56a70%不明1
222GLM-4.5V 2026-10-28config_301272a787121a72765e29a7470f50f9a58d0bbe0172f3e41a0cf0b5d6a37edb70%不明1
223Claude 3.5 Sonnet (20240620) 2026-10-28config_5e52fa7f1c137d072f2c1e4f3800c27505758a4dc9c455f2212b12dad056080a70%不明1
224Mistral Small 3.2 (2506) 2026-10-28config_917ddf10b983fe9ca8fa2aaae0e1fcd1342ce49cb1a9ecd19cb1da78db39b68869%不明1
225MiniMax-M2 2026-10-28config_d3e0b9c9fa5a087f33c0363b1912d232e0b3e70fa39a6f2c96d6080d7290e45569%不明1
226o1-mini 2026-10-28config_8a9f2fc8e367c15782e007f2375395f950d1a3a2ea8a10310c80cdc05f8fecfb69%不明1
227Qwen-Plus (0125) 2026-10-28config_048d2f180d394cd1c15348f368a81768a0d57267ae20d5cc1a8b1a0a132df2b769%不明1
228INTELLECT-3 2026-10-28config_c0544d0781167558bfe124257d610b65922896f9aa84035372799546bbb096d669%不明1
229Gemini 2.0 Flash-Lite Preview (02-05) 2026-10-28config_7b02401ce95bb2dbbaa4db05ed45b858e35a9e1df236b5cb5dfbb94efd34391369%不明1
230Qwen3-32B 2026-10-28config_0406add03f53242598d80da8c3821462a008dd51a1814c1b0ce3f380b2310f8469%不明1
231Amazon Nova 2 Lite 2026-10-28config_b729d716d78260538adf6a41f5ef52a87f6fa84e8243b0e1fa98ea2c7ddf98b068%不明1
232Mercury 2 2026-10-28config_6cbe61b908e09062a9ff0e49925c63de967cba06f4170aea35f759c1d475b74b68%不明1
233GPT-5 nano (High) 2026-10-28config_43ee65b6cd2fb7855a15ea374829d09cb9c22fa1107a6c1e866e8c41ae2830fc68%不明1
234GPT-4o (2024-05-13) 2026-10-28config_0c0670073af8dc96956bc49395794bd6c025b14d8c09856b225db26e232c76bb68%不明1
235Llama 3.3 Nemotron Super 49B v1 2026-10-28config_7e4d9f596cc26f21da70e95c571f46aac4552d7af5085cb51b55bbebd98fef8468%不明1
236gpt-oss-120b 2026-10-28config_cd81f8e6850e09592618f5c6dc7c913b7a577214403952b228a76a885445678f67%不明1
237QwQ-32B 2026-10-28config_369a6e94217632547609b80917c7102ff5284dc5966011273509cf5aef4972ce67%不明1
238Llama 3.3 Nemotron Super 49B v1.5 2026-10-28config_68732a5b34793c3b3a1d2ec86bd82559b17b11e75edfcf456e53fdcb11b167c867%不明1
239Gemma 3 12B IT 2026-10-28config_37274ad52fe604115c644ef15cf24a2c3a06594424ce32a78adbb1e6e0db78ca67%不明1
240Olmo 3.1 32B Instruct 2026-10-28config_0be10e4cc42765da097a7e51ebbe9c55139a32434fc05158f3792ad8c391a27c67%不明1
241GPT-4o (2024-08-06) 2026-10-28config_a4fd81959ae45d912bc6bb1be69f90799ae4de7b9e2c031b84d7b63901bd8c4f66%不明1
242Gemini Advanced (0514) 2026-10-28config_cc9398698f0df6a3f889395f7844e45c9eb5a025f5e031a4a61793158dd634b366%不明1
243Ring-flash-2.0 2026-10-28config_08a8a6e1f883ddd93c2033d0fbb431fad29d9455614f7ac2b5e382c0cf0bf68666%不明1
244Claude 3.5 Haiku (20241022) 2026-10-28config_4e1f26f75a8e0fe2a96047bf2a0ffd69a9ce1e1850d7480e32bbd6a889f1b5cd66%不明1
245Hunyuan Large (2025-02-10) 2026-10-28config_92d99b0f387374fb8027c2030b6fb6e05f8f4b53ccab9ac7e4aaf116229e436f66%不明1
246Step-2 16K Exp (202412) 2026-10-28config_056e2cc252aa85973f326c68e9a25102117c78491ef2fa9f9b6ace08617916d166%不明1
247Ling-flash-2.0 2026-10-28config_6acf91647b1a1eeee3111194e21c7e4f74904d522269fc04ff8089c456eb0a7066%不明1
248Llama 3.1 405B Instruct (FP8) 2026-10-28config_d19fec3820dcfab82dd21f2c0a6bbe2928c221e25aa4abf6a49b9f9e27b0bf6966%不明1
249GLM-4-Plus (0111) 2026-10-28config_8d656a0cc7a7f4e0663e897b5949b4010c6384c8d1a5c6d322195dce8d7bfe3866%不明1
250Claude 3 Opus (20240229) 2026-10-28config_2e2a4886095f1a076773fecf4f1d55538cb51f97192cb482365c4250e6d161c066%不明1
251Llama 3.1 405B Instruct (BF16) 2026-10-28config_12a48d675424669dfda877181ec4d6cad7e5f3364562afeb090151b1331e12e866%不明1
252DeepSeek-V2.5 (1210) 2026-10-28config_216501170ba4f8adb5a1daf94a180e3aa908046fcbd00d1f0602c98bfd89252d66%不明1
253Llama 4 Maverick 17B 128E Instruct 2026-10-28config_60f40c4baea0dbce927be57712f1506f8635d2cf6267810242d4e492f04a991866%不明1
254Hunyuan Turbo (0110) 2026-10-28config_d97eb3128a78a1181ac709250bc75dc26e4d8346f804062d9456a6d894916da166%不明1
255amazon-nova-experimental-chat (10-09) 2026-10-28config_d8594458cdb51534c848fd24d6b0d755951569f771e54f583b7de8f00a555f4b66%不明1
256Grok 2 (2024-08-13) 2026-10-28config_2fdd74db5ba6045754103c42a7f487d0f2f381c7ac363788cb64d7bb24e943b365%不明1
257Gemini 1.5 Pro (001) 2026-10-28config_c48d7b2b2c07f23519166543c47196282b339b4e7330ede89a4e96711fd2b98f65%不明1
258Qwen3-30B-A3B 2026-10-28config_613478f5a0d321c07892431b73e4f6310fca76cafb8043fec084f8a1c4f343fb65%不明1
259Yi Lightning 2026-10-28config_42fe9aa505ea7be7c8099cb1f070a15996cf1ac85cfbe4bdf8b7caf06b3065c065%不明1
260Step-1o Turbo (202506) 2026-10-28config_4fc175bc80c574203538d9673749d324893d84ac0137ea4dbb45dc4224ab7c6364%不明1
261Molmo 2 8B 2026-10-28config_6b3d274a6cfffe6505a31b204a973674efe5f28c0be1b9d355e23fdae01f95a064%不明1
262GPT-4 Turbo (2024-04-09) 2026-10-28config_b6c8d3ee554c6d20bb11a2e0f705e6cd186866b83d63599eb7b684954669049a64%不明1
263Athene V2 Chat 2026-10-28config_30b2efae25f04816f9d5cd4a0a65797a0aac73d528aaf0e31ab52092169fcaef64%不明1
264Qwen-Max (0919) 2026-10-28config_c3b8e1e22cbb01de925bd9e41da7f5f9e156c6b135049134f3eabae4cd30e92d64%不明1
265Magistral Medium (2506) 2026-10-28config_c017f6a2ebdae779199b6d065b92c6dc40e7d349502cd3076dcc8939eade89d064%不明1
266GLM-4-Plus 2026-10-28config_8042a45148fd9bd00ad97c6aef5f48668b14318d712d3499b0d9c8164f430e7b64%不明1
267GPT-4.1 nano (2025-04-14) 2026-10-28config_b1a3ac8175ffdf0c6d2d2eed4f60c7eb67ce457804f968150e0423559a4b461964%不明1
268Mistral Large 2 (2407) 2026-10-28config_10540aeb8704c993ec94b43a514a6c5d662a38061d93324bc92691963ff4b0d863%不明1
269Llama 4 Scout 17B 16E Instruct 2026-10-28config_bd783c3fde9fcc62fc73ce933688e2c2d198311c9f71ebdfe5b3bfca19e55ccf63%不明1
270Olmo 3 32B Think 2026-10-28config_0f60b164f8fcb19e640a47776a4f671ff50a52d17218c09ac0fa840474850f0063%不明1
271GPT-4 Turbo Preview (1106) 2026-10-28config_df733624af26940f6e926bafe992f473389cdab6e3c21494cdca88b1f123d77463%不明1
272Mistral Large (2411) 2026-10-28config_ae087ba17ad4e564ee63fbe13ab8d95d930263b51246df0393b01a56c10dcd7963%不明1
273Qwen2.5-Plus (1127) 2026-10-28config_117f78a42c43dcab3f8de20bf50f2d1872bfcb76d396eb0d8b0cc6acd9a0757863%不明1
274Mistral Small 3.1 24B Instruct (2503) 2026-10-28config_3fe11e8cac0bd462829aa1a599cf9e5c368cd23f2b20f514977b09494c03fae262%不明1
275GPT-4o mini (2024-07-18) 2026-10-28config_c55f72e2c521f7384e637d511d540098ba14977e4d5847dffcf5f30de3e6b0dd62%不明1
276Llama 3.3 70B Instruct 2026-10-28config_9fc11fe7c5fa8810d95f76d1e4a7e803b5045227c88ef58962cc52b24eb1fd9f62%不明1
277Qwen2.5-72B-Instruct 2026-10-28config_d35a8469b699c57386c0542598929c6798b6018e8c2e4f64a877c56a3ff1065062%不明1
278DeepSeek-V2.5 2026-10-28config_2bf5ce26ea016cfddbdb2583e49d67bb4d200a8e4455d2792954e8fdfb615c0362%不明1
279NVIDIA-Nemotron-3-Nano-30B-A3B (BF16) 2026-10-28config_bcbc73725065d116cc14568646fa4d35688c5aaf0071bf43ba48f6eb1946b36462%不明1
280GPT-4 Turbo Preview (0125) 2026-10-28config_a978216e55085539c5f99ed90d6936eac0e8e96f5120365a45b43753d9aac31262%不明1
281Gemini 1.5 Flash (002) 2026-10-28config_a053db9d42f67977d5606caea2f75395d036aefdd842427da98d8cc50851bc6862%不明1
282Hunyuan Large Vision 2026-10-28config_7096b03fe6ce8ca49c8b10c78a02d22a71237f25a5c9c7bc4f0fda919850fe2661%不明1
283Granite 4.1 8B 2026-10-28config_445dd8be849e8ce28a96b69713ad9045434ca7cb08abcd17b3f11433f5cdcc5061%不明1
284Granite 4.2 3B 2026-10-28config_2b5309911611842d25fe6157c932d88f7ba485b19309edc8c09423ccd7a0d8f061%不明1
285GPT-4 (0314) 2026-10-28config_7111f224447b8166ea5920a6272688b7f91762082aa796c49bc8ecc713fad8dc61%不明1
286Grok 2 mini (2024-08-13) 2026-10-28config_b459a64d82174432df05543379ca66c57cef5499e49ad5fbefc4c6c59ca3edcb61%不明1
287Granite 4.2 8B 2026-10-28config_db98d68118c3697d3f68fad4ecf4245ca09084c64bd2c4d5b8b01ea76281266261%不明1
288Gemma 3n E4B IT 2026-10-28config_b64fbc5028e0a12425641f0030f2cde139ecfd6279c9c852265374127b32fe7a60%不明1
289Hunyuan Standard (2025-02-10) 2026-10-28config_e91d0e4f836baf778e0c882c95eb0f97a6e8cbc50035b40c786621ba3ad9bb4260%不明1
290gpt-oss-20b 2026-10-28config_a4fbbd7aec021db8f58fcc17c17c5c1f876c8b709cbead372d046cada445d20060%不明1
291Llama 3.1 Nemotron 70B Instruct 2026-10-28config_5b9324345a033d6fc0fb462d013f67b966cab44f9964658b8accf58ce674d38460%不明1
292Olmo 3.1 32B Think 2026-10-28config_eaad70be49355c103a25f2108c376238fe562e0d4ef5982e85d87b849374716260%不明1
293Athene 70B (0725) 2026-10-28config_fb731f73c4ebdd009e6887f30290de01c580e385a10f256e5cb48b47a597a03160%不明1
294GPT-4 (0613) 2026-10-28config_c4bb6bed8546f9c9358ca16bd3d6c4420dd57da4bd522cafb710ee08e3c1c71e60%不明1
295Amazon Nova Pro 1.0 2026-10-28config_e597a4a506d487b5f13b830409ddce55b5606418f92bebb5c866bfe0bd83bf2860%不明1
296Llama 3.1 70B Instruct 2026-10-28config_a6c6d0ddfd1eb52fcaad3b9dabb21d2623662924d9f50dfd1e5038bf6709a04d59%不明1
297Llama 3.1 Tulu 3 70B 2026-10-28config_d31547493452c3b555e337fccc6983ebb82647db85eaf6ded114dfa81f8d4d6859%不明1
298Gemma 2 27B IT 2026-10-28config_2b3e3e1cf8b0aeb319507404fa14235decd5210cb113fb6ea9d4c7fef8d2ecf859%不明1
299Mercury 2026-10-28config_4c7e76eb4123ab2405f6f7d69e731d1b84701fbd5ab37dac76cf76f829f2723959%不明1
300Granite-4.0-H-Small 2026-10-28config_248a63a3deeed0571aadd6cd349b0322ba9dfcd919000dde09903c142dbbe73d58%不明1
301Claude 3 Sonnet (20240229) 2026-10-28config_3c0899dd553841eeb947f66c3de3809855d86ee3f8b01dc8d254ad9bd460b64458%不明1
302Gemma 3 4B IT 2026-10-28config_4aa7dc7b9aeabcebaffea25ad0598e9d6f4ce3c83ba4eab5a90d8ede8086bad658%不明1
303Jamba 1.5 Large 2026-10-28config_b4089449edad80a0ad30b289c4adba2bf2c0e09661ad053fb98335d5c6fc84eb58%不明1
304Gemini 1.5 Flash (001) 2026-10-28config_f27904e22adcdc350d309ad3f90e84e52c0e6063e3ce547e24211bdc41ac23f158%不明1
305Qwen2.5-Coder-32B-Instruct 2026-10-28config_b68b7d03ed1655359feac9b3cfc01fb87c81d762769de4488294c270d74ca2b658%不明1
306Llama 3.1 Nemotron 51B Instruct 2026-10-28config_f5c46367fcd79da1b67e62857cb379b8292716d1bc371897583ab51063aa55d857%不明1
307Reka Core (20240904) 2026-10-28config_74a6fb76e35627ea78093b85a75ecb61e233ec4da01e568311c46b47970e38e357%不明1
308Nemotron-4 340B Instruct 2026-10-28config_bdbeaca685e8d03b2ac35c97bf19f70bcdb172a421485cabc676376f3f54be7657%不明1
309Llama 3 70B Instruct 2026-10-28config_85c5443359e75a3e10041dcc2eeb7e65d6c049662850b4f6c7c26a6bd5c25c3d57%不明1
310GLM-4 (0520) 2026-10-28config_85d9114f65dd0894dc9413dd3a876f5508d422783bbccb67474e5cd5bb90c13256%不明1
311Mistral Small 24B Instruct (2501) 2026-10-28config_b2c7b0dc1909a29ce3f88eba984f71b68e49e230e7dacbd5830afc71a79cf49956%不明1
312Command R+ (08-2024) 2026-10-28config_7aace54de7849d8513d2ef70f80e1669e8d26082ea44aba2f3d664c0042cccd056%不明1
313DeepSeek-Coder-V2 2026-10-28config_87801524586e28c871ac8071b94a48465e05254fb8652296b800fd13974b5eea56%不明1
314Gemma 2 9B IT SimPO 2026-10-28config_5b8f13067116141c0538b485934d5a81669bb1c48881c81ac68fb380defa735e56%不明1
315Reka Flash (20240904) 2026-10-28config_b4cd1b55b31e9bd78d7834f42097a511763368425caaa19aef139e7f2dbcd34255%不明1
316Aya Expanse 32B 2026-10-28config_3408208375bf1f95a940116f0a3711090422a1b08398cc530a953de2d138755555%不明1
317Phi-4 2026-10-28config_927a08f1b103a1908b7ce1bc716b45a5d51e20be32f992cdd9fde7f01fb19b5055%不明1
318Claude 3 Haiku (20240307) 2026-10-28config_5d7c0a18dff114b80bb8f636554b51256479d626d4040fcd729666564981dc0155%不明1
319Gemma 2 9B IT 2026-10-28config_748f53ea872d019fbe6f957001412552fcc42143aac03bfd726687c0aa2f486b55%不明1
320Amazon Nova Lite 1.0 2026-10-28config_5a1bcbc9c18ed0f1edf60042d7e643587655a3c1f4eacc8ee19f8affb79bb0cf54%不明1
321Hunyuan Standard 256K 2026-10-28config_a894b35264b32f65395a740b23013adfb386dd3756d6c90906b947082644720254%不明1
322Qwen2-72B-Instruct 2026-10-28config_1a29b8f40beb137e6773b86fb49b322e3f9dd73fd870b1fc4970ebd39688683754%不明1
323Command R+ 2026-10-28config_ca9553fd86a2f5790a4a9599de0ae9d4fefeec996ecbb892b5005e4912b8b7ca54%不明1
324Gemini 1.5 Flash-8B (001) 2026-10-28config_2f6346534aef856512ad1c877d7f9fefc09d877a228d9fc348376ba73703747453%不明1
325Mistral Large (2402) 2026-10-28config_484f35aa55ce002a0cd0640aa8abc2121e13869f495a6520bf2047550f0b3bf353%不明1
326Command R (08-2024) 2026-10-28config_c67418265a7d9263a6c8a1d9db4004f889edc8e6da7eda4a0a7035fbe078ddd253%不明1
327OLMo 2 32B Instruct (0325) 2026-10-28config_d7b72eb69d271934c6bb970a8886f8bf6986dfc866fb06d2eb06773874d87fc552%不明1
328Gemini Pro 2026-10-28config_3cbb09862e8f1e00520e4e0c86385a932c6c63a41cb3af03be051640ed7b234b50%不明1
329Qwen1.5-110B-Chat 2026-10-28config_39d177c0e248ffc1ae08d00847bece04d45f6366cd42cef962063347397fcaec50%不明1
330GPT-3.5 Turbo (0125) 2026-10-28config_bc3e0380b83d6e5c7b488c5d8aa7253a6e63aee1dd390c56bcc32123cf90dbe550%不明1
331Mixtral 8x22B Instruct v0.1 2026-10-28config_1e96141dccf79ef9c2cc2bfd197cc7ec096f72300cd92d70cfcb3f1e9347b79550%不明1
332Amazon Nova Micro 1.0 2026-10-28config_3603c39ff783f7fb2a772997ef84c737f453afb422c5896e6a84a404d54b169850%不明1
333Qwen1.5-72B-Chat 2026-10-28config_a9f2ba029dbd5f8efd6b832ef62d18004a5561761c5012965698e694a0ac091349%不明1
334Ministral 8B (2410) 2026-10-28config_1596d4951c8de17f0b024ea0a421407f2c892412cb163c4c71a96f179a7c958749%不明1
335Mistral Medium 2026-10-28config_6215b90e391b25beeffb1525e6558bfe10123e3e2718c5d1abacc20c166a798549%不明1
336Gemini Pro (Dev API) 2026-10-28config_f9fef3200c3a4b802a33ac4a06ef8e86718ecea8c7f42dd7396157faa4e42a2049%不明1
337Llama 3.1 Tulu 3 8B 2026-10-28config_5cb2cdab009483729e486432511caf2890bc25450af5d13056b0a55bd67f80cb49%不明1
338Jamba 1.5 Mini 2026-10-28config_be058c6714689ea73bdef9c69b742219d7b56df96a163f5bbb84b99bfdbd7bc248%不明1
339Aya Expanse 8B 2026-10-28config_579c07982af14313eb97a04e27e61343847ed8de3ca9e471fe333cc943c394df48%不明1
340Reka Flash 21B (Online, 20240226) 2026-10-28config_ac643e7fc9dbf0e8c6fab6a9c6ad1d396345f0fc970213bd09f03fc21d5a873348%不明1
341Command R 2026-10-28config_245aded02f8f5c56174476aa6f2f9c610d046de1480c758c57748d598fc8952147%不明1
342GPT-3.5 Turbo (1106) 2026-10-28config_3c2ea7d84168e2e296b359794838c62ec78899c7675cff54e65d5573f0769c5347%不明1
343Zephyr ORPO 141B A35B v0.1 2026-10-28config_14f6d11e03c30ddf99d8e4ec094eee25d1cd276523b57f08b747764be89f05b846%不明1
344Granite 3.1 8B Instruct 2026-10-28config_625cc3b2c4afb600a97f77d1d0802424664a0e0e624a147bf61148092ab2bd9046%不明1
345Llama 3 8B Instruct 2026-10-28config_320f4f08221ea22ea611cf391257ebc7376200442e54f0d0178109706942541b46%不明1
346Reka Flash 21B (20240226) 2026-10-28config_5c93e7cb295ddaae1ee01237c0449ac9db74807fefe8f9f21b6363242303176046%不明1
347Llama 3.1 8B Instruct 2026-10-28config_8be5ab50756c844d9ba66047e6610dd081ee65e6ab7d99c16b1fd0861bb1776246%不明1
348Yi 1.5 34B Chat 2026-10-28config_c84fc3fe938ce53cd42c4d820e7f0b9dd99db0419a7a71676cecb0eb479a7bc245%不明1
349DBRX Instruct Preview 2026-10-28config_e82b88296539b9d8459919437acdf8efb92353807813d17902a4fe02fb43dd0045%不明1
350Qwen1.5-32B-Chat 2026-10-28config_c7755d6a6ccc34bba411ea38a81b051c0853497e707eb53e0446b9d2bdee060845%不明1
351Mixtral 8x7B Instruct v0.1 2026-10-28config_ad3d2cb0e3dae6b4b17ed0cad289dc5845d2c8debb99b0876be650e18027706944%不明1
352InternLM2.5 20B Chat 2026-10-28config_257eabecb81cc5ac0f4af33ecbe4e4e62c5c5c297ab0aaec5ab2710b504ca76444%不明1
353Phi-3 Medium 4K Instruct 2026-10-28config_fe6c929b53e04e4bd68d53e37f693478152b800c9dcb7cb6b7a7e599bc91456944%不明1
354Granite 3.1 2B Instruct 2026-10-28config_ea0d7fe63ba900a8fa7694e71b616f013298f8fa31cb1a234e5f8b4a8b3e2be243%不明1
355Granite 3.0 8B Instruct 2026-10-28config_fd7f6c4ebba33a578fa6c4ba981b1829571e5c300d64586b7e31c3813569b67243%不明1
356Gemma 2 2B IT 2026-10-28config_c9b568e67d4cfc257d469b8615bb1ee63df942520f02ad30654867b413275b9443%不明1
357Tulu 2 DPO 70B 2026-10-28config_8068e2a33b21b6b3eedcf7c3ad0b2b6d6a611f88582ee9e664a78d38536c90de43%不明1
358Qwen1.5-14B-Chat 2026-10-28config_6a5fb2134153e18289b34d87272c8e3057b9bd5fcb4ac223e620890304f1826542%不明1
359WizardLM 70B 2026-10-28config_b20df0351e347bb88266462f1f5a19f24da04e76ea09825d9369b4efe35d6b5541%不明1
360DeepSeek LLM 67B Chat 2026-10-28config_14cbaed7a7b27f8a8ceeb47c572e245d3cfcec3c920edc5b3f76606d95452c9f40%不明1
361Gemma 1.1 7B IT 2026-10-28config_1ae2478ef3cbb132dbd329e94e4dbaca78fb727915b1bf95075b07af0d5699cb40%不明1
362OpenChat 3.5 (0106) 2026-10-28config_2f38729327636377ee9787611c73799618ca1273a20798472f380f2420ed0ef240%不明1
363OpenChat 3.5 2026-10-28config_44728bcd1f37d5c4e413d3697ad68f25dd37fc679dcbc10e1226d4a56fe0394e40%不明1
364Phi-3 Small 8K Instruct 2026-10-28config_dc09f69a626506ea584572a33c2a0c660bbac0308ab32b4423184eb3f39eb91040%不明1
365Snowflake Arctic Instruct 2026-10-28config_c24ce8c0d96c698b9a4bb085f55568817342637dc6f52e1e19c61bc894c82e4e40%不明1
366OpenHermes 2.5 Mistral 7B 2026-10-28config_fdc66993af16838436484f6108d4e00e6d405b284a9cd004e106741d9e94331840%不明1
367Yi 34B Chat 2026-10-28config_7cdbee6291bb8d54014f0ae93661f35b1ae2d80e6977711975a0d48fe61b3aec39%不明1
368Llama 3.2 3B Instruct 2026-10-28config_a647a980d1dd166fec4d8f43c4099a86dad686aea89f2228c56f0800b3e0faa438%不明1
369Starling LM 7B Beta 2026-10-28config_a8a1a61aa8eba48cccc709426f6518b85be122007ba525bb631641e291f147d338%不明1
370QwQ-32B-Preview 2026-10-28config_5358c615d127ac39c79ebe571e41c8b39b2761efcc07ee13b3870c6cfb3d5b0438%不明1
371Vicuna 33B 2026-10-28config_37b0448e8ac70bf2c90e19b3ba3a0a329df4584b369524af8b586a8659720bc737%不明1
372Starling LM 7B Alpha 2026-10-28config_6ea47961fd43986f7432defa95a072bd1fade2ba2cf46f2821de1cbc8f0034b437%不明1
373MPT 30B Chat 2026-10-28config_e585fa122ccee48e87f5ff01705e3ae06647b8a8b97aabe7e62ef27d41e7d61937%不明1
374Llama 2 70B Chat 2026-10-28config_a16c1c5968cf5043cc804a1affd407158456a6a7c18a07873ea28766fd17426337%不明1
375Falcon 180B Chat 2026-10-28config_669d597173180d2225aef0ccdd27c80db6dc2e4781988406ce345d69ea480e4637%不明1
376Granite 3.0 2B Instruct 2026-10-28config_84321f8ab34d8f0fbbdd440de2338a5b089db059ab31139333c624db5cc05a8436%不明1
377Dolphin 2.2.1 Mistral 7B 2026-10-28config_df11fbace351c7c1ae4f89eb9ebfbb01973f61601a697f303869c45296f3838f36%不明1
378Llama 2 70B SteerLM Chat 2026-10-28config_ecb9cba451d1ead4c47aa1eea83032fe1cb10cdf1afba73a6abb345e30d53c6435%不明1
379Phi-3 Mini 4K Instruct (June 2024) 2026-10-28config_1304c7971e4a06e4cd9c53a31fac0e09818c98f88b794b9065044099d0791bb635%不明1
380WizardLM 13B 2026-10-28config_0db445db3af4493d5eb0e6bb54455de456674fe16ccdd76c9568de50724cda5735%不明1
381Qwen1.5-7B-Chat 2026-10-28config_6df9982ed047181f8183f9e9e332542b1820fd3e1017fbbb86f2b5bf97f8a78835%不明1
382Mistral 7B Instruct v0.2 2026-10-28config_a08b2f220d19f58fa387c935418486d1246f082873fbaecc8c765ab61f21cc2835%不明1
383Qwen-14B-Chat 2026-10-28config_72caebc63d0e95c5b3b2b9b595938cb10206d821a871c560541266068c62247b34%不明1
384PaLM 2 2026-10-28config_4deadb80dff2e4c5832b08adfdff42ef95471ebcfff73063b82be3401f94f07034%不明1
385Vicuna 13B 2026-10-28config_c230765e3740524e07beb7be493d2c363eb8b5ca69c5fb5aa5424ea83421e08534%不明1
386SOLAR 10.7B Instruct v1.0 2026-10-28config_216d7b302cb42c47ad2f2e51048008cca5a15471ef80ba307871587ecfa578a934%不明1
387Phi-3 Mini 4K Instruct 2026-10-28config_a64b9f3c40b79dd391fe069cb42cb7389694fa6d509fac198b7db76c1bcf586d33%不明1
388Llama 2 13B Chat 2026-10-28config_0939f813fd27845d87d7ab14d1635d1366c17ebe79f6f0c65acedb5f4d648baf33%不明1
389Nous Hermes 2 Mixtral 8x7B DPO 2026-10-28config_21dfc63939c5467cbedf01ddd2eedd249cba1255b34824c539e3c9172238c09d32%不明1
390Gemma 7B IT 2026-10-28config_f129902f0121f8232db034c58cc84a3693f0fc696a92e36f84dcb7490bc2159032%不明1
391Code Llama 34B Instruct 2026-10-28config_7aefe6a1259cfe02d33b7fa1df5d169450f330dfe0c220ec6ec5c2edc5d75fc732%不明1
392SmolLM2 1.7B Instruct 2026-10-28config_ecd9addb9449c0be72ec1790afed95fc6ab93f0fa18b4531ab50a9c52e3bebbc32%不明1
393Gemma 1.1 2B IT 2026-10-28config_1be1529d9c8d211dc71343e3d8252421562844730de5286876937598503057c431%不明1
394Phi-3 Mini 128K Instruct 2026-10-28config_02e60a0b34b14d8bfcb07ddf2adbc8999a42998069b3796979ca6f4a49c2b1d731%不明1
395Zephyr 7B Alpha 2026-10-28config_5c0d50d6c4827ae22550fb859a1e8afeecd7c46d0150d5b354d1a793ca113b6a31%不明1
396Code Llama 70B Instruct 2026-10-28config_42c1006c4640b83fdefe9f7d4ecbb2e061fd994492710e73a6f7388577520f7c31%不明1
397StripedHyena Nous 7B 2026-10-28config_a4d2b4c97640512a430583fef43a73433c05d3eef25bf440ed9a4925c999c65029%不明1
398Zephyr 7B Beta 2026-10-28config_739bcf073e276a00fd4f907ccb3d6db27fe49cadece35ca3dec8ee2d3f256a6c29%不明1
399Mistral 7B Instruct 2026-10-28config_80bdc87d6af9f08e884fc8293b74049f793d796bd30298447ee108e9806ab17929%不明1
400Llama 3.2 1B Instruct 2026-10-28config_2626cbf7c0f5e2b95795c6e978dd6f48bf3792a4909f92c87b416c2e8cc3fd6a29%不明1
401Vicuna 7B 2026-10-28config_a4b5aaafe4210b33e599671e2cbbd2db985c50b7fb90a03efef2d19f0228d53a27%不明1
402Gemma 2B IT 2026-10-28config_0eb12fa2281cfce80e62684264176aca1fbdf5922b71a74c3dfdeca8f7d674bb26%不明1
403Qwen1.5-4B-Chat 2026-10-28config_f02e9693e4e257c29a3b9673dd851ae10fdd2f846ae8482d3b053fc3883a9f8126%不明1
404Llama 2 7B Chat 2026-10-28config_87ec21c709f2631513c9cbcc2b3566c835431ff17703b3df5299b27c9222f21326%不明1
405Guanaco 33B 2026-10-28config_b5196f6d62c612126a5a0e18e9e39d5fb6d78d9a0707b3ef3f7feabaeb567db625%不明1
406GPT4All 13B Snoozy 2026-10-28config_a7024ce29569a3afafd4f9c75b7a74da36f5ffaa06b384cc23ff7221eae7d8bf21%不明1
407ChatGLM3 6B 2026-10-28config_ba3353056b710abca3b086b939390f1aa51103f07854a862e6949d96ed6dca6b21%不明1
408OLMo 7B Instruct 2026-10-28config_e36b4602b25f9a8f3fcd90fc34a12d94b09baa7002bc17c07dff18fc418fb6e719%不明1
409Koala 13B 2026-10-28config_c390501080a267267d400a51837a1481270bcf419a4758728bffa761251f026519%不明1
410Alpaca 13B 2026-10-28config_5d07d2245ba44ccf196c35e87b79907d6975119fe0cdbfadb71f5cc1f24a31cd19%不明1
411MPT 7B Chat 2026-10-28config_74e6f6583d767ac6db033de8d40bc3aecada9d17bf35b9813f4bcaa5c3155cb916%不明1
412OpenAssistant Pythia 12B 2026-10-28config_856a63d4405ba11a703cafdab52233a61120ed48a0453b482fff14ec361c345013%不明1
413ChatGLM2 6B 2026-10-28config_d46d1c233e711496b3c2a7929636720306b0d994ae0dd8f4ef8a30e4b7b6e25212%不明1
414ChatGLM 6B 2026-10-28config_3c9881113805b1d20eff939425b6863a5dce32ae62ab1a7a72237598f606732111%不明1
415RWKV-4 Raven 14B 2026-10-28config_a6632b4ec49c4fe60879a1d42bdf1343d73a07422efe1028c361ae63710f7e7810%不明1
416FastChat-T5 3B 2026-10-28config_f1ec5003fc2a704dba99571e8ead7e47956921bc26f1241bad96aecd234363998%不明1
417Dolly 2.0 12B 2026-10-28config_289ab22854d665c2eccf70f58d57a1c8eb5350f094c84e3adbcbe913d849e51a5%不明1
418LLaMA 13B 2026-10-28config_8ed217e2e6feca55490aa1b61dfad5fd6baf4fba27b8e7baf4aa71fa3f575ad11%不明1
419StableLM Tuned Alpha 7B 2026-10-28config_cb9a71f9301263a8202ebc7cbda815f58c0e4c832a9e4a4efa3d9fd4d7cbf31b0%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。

モデル構成 · 直接プロンプト

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

エクスプローラーのエビデンス

EQ-Bench Creative Writing v3

単一の出典。に確認しました。まで有効です。

RankConfigurationCapabilityUncertaintyFamilies
1gpt-6-astra eqbench-creative-writing-v3:gpt-6-astraconfig_5d6bf8c53cb26bf8521ebe87b0a9374162cd19e292282a1d9b4cce0dcfc282b8100%不明1
2kimi-k3.1-pro eqbench-creative-writing-v3:kimi-k3.1-proconfig_44910e11248f755ca8a49be92fbcd5b87dd9293f17fa44c6ec2df61aabbd6246100%不明1
3claude-fable-5-1 eqbench-creative-writing-v3:claude-fable-5-1config_ccbbdba3101f5a94a3e2b22c612a5cbaba1ce933cf41d794336a9ea999a8028599%不明1
4claude-opus-5 eqbench-creative-writing-v3:claude-opus-5config_2bb4b09520702dbc44d1cfa24afde3aa1f7daeaa58db6e2bc72fbf1aaac048ad98%不明1
5gpt-6-sol eqbench-creative-writing-v3:gpt-6-solconfig_0d82fad68571409b4f74ec51ff8b8e205a77af15d6ee1b4efed8b83336e0870497%不明1
6kimi-k3 eqbench-creative-writing-v3:kimi-k3config_d66c6e07fedc532103cff26a3a24b654216470b82fa4599cbb46193cc807d68995%不明1
7GLM-5.3 eqbench-creative-writing-v3:GLM-5.3config_f586b196e68a400a362be2dac10bf853d7f1b9f0e5ceaf0094f5bfe828c7371495%不明1
8claude-opus-5-5 eqbench-creative-writing-v3:claude-opus-5-5config_fb88d7ed89e0848423d17b1516b999b32e2b06f7e56a9d2fc98550f7e54b546194%不明1
9grok-4.7 eqbench-creative-writing-v3:grok-4.7config_42deafa20e788bc8a7db748e9f4f82f4f1dd6fb918600197ab2c001615933ab692%不明1
10muse-wonder eqbench-creative-writing-v3:muse-wonderconfig_f708cfb1402048775baad32b2ad71daeab738a5294f18c6e55ea0bf860032fc291%不明1
11ox-alpha eqbench-creative-writing-v3:ox-alphaconfig_486d9b10f66752d6abc7b026b85d3683dcf3c463f534fb2f60ff6fa211b4dad290%不明1
12gpt-5.6-sol eqbench-creative-writing-v3:gpt-5.6-solconfig_516bd36bbf36a83e6b90c725215d4f8778ca8cd3c0868adf6b7a9dbede3e9b4c90%不明1
13claude-fable-5 eqbench-creative-writing-v3:claude-fable-5config_7cefec8125589b75fdfff227253a1490581e40518d3661dca9eff88e16a1260688%不明1
14aion-3.5 eqbench-creative-writing-v3:aion-3.5config_067e7478aef2ad2cc6da6a7c9a11ee28b8e40e3188aecae71d3e6b831430243288%不明1
15muse-spark-1.1 eqbench-creative-writing-v3:muse-spark-1.1config_579e4081a8fce9d2b5c2e11093a248276270f89b5cae8d2922f0c067d353a94187%不明1
16claude-opus-4-7 eqbench-creative-writing-v3:claude-opus-4-7config_01bcc45834422cf534a93830da9fc78e8f487b991a581c53100d5e95b723152987%不明1
17Altworld/Hemmingway-1 eqbench-creative-writing-v3:Altworld/Hemmingway-1config_893ca0b03a4739b9993a7e85b7e610586631b1150f669236d4ab397cc6e5bf7b86%不明1
18muse-spark-1.3 eqbench-creative-writing-v3:muse-spark-1.3config_47ccf337fa4000d56b5603385d8df0a90f6e8deca396b6228f2201d32c67379586%不明1
19gpt-5.6-terra eqbench-creative-writing-v3:gpt-5.6-terraconfig_50f01085ac6c4719d91d729d916b1ee335b701c27006bd3c0d7983917889f2db84%不明1
20gpt-5.5 eqbench-creative-writing-v3:gpt-5.5config_3ea65ed4ec66a78fca6a2246e182f2b7f3ee939fab745a04ef4890755af30af683%不明1
21Qwen/Qwen3.8-2.4T-A95B eqbench-creative-writing-v3:Qwen/Qwen3.8-2.4T-A95Bconfig_c16d36887636aceccedcf718ae4c05f6dfa08e81a088877175ffbc88305f72d483%不明1
22muse-spark-1.2 eqbench-creative-writing-v3:muse-spark-1.2config_76f5a7377262e368e22ed254e5d69983dcc29ec4922134d13d73b7171711cbd283%不明1
23gpt-5.4 eqbench-creative-writing-v3:gpt-5.4config_d08804c902565d92e66a8743f122a19a4d42c3f50eb40d37e9c0ce58cae001ff83%不明1
24claude-opus-4-8 eqbench-creative-writing-v3:claude-opus-4-8config_5b0efff2e5610fc91d67d1a85908c07f86c9d49e937fa049aa5065a7f143a9a683%不明1
25gpt-5.6-luna eqbench-creative-writing-v3:gpt-5.6-lunaconfig_ebb5007e7dc7510da39caf28fe11774eb71f6cd6e9e05ed513ef5cde5eeec24183%不明1
26claude-sonnet-4-6 eqbench-creative-writing-v3:claude-sonnet-4-6config_e92649a11ff34fca70cdb33863ae411f957549856f7367d18aceed42bf37119081%不明1
27claude-opus-4-6 eqbench-creative-writing-v3:claude-opus-4-6config_df5ebe42f50cc26f10d8ee0dcf074901f3b9dd29679bfc5f67f571c28e1c401081%不明1
28meta-models/Muse-Glimmer-30B eqbench-creative-writing-v3:meta-models/Muse-Glimmer-30Bconfig_e1820b3ff465def5ebdabc5b3d57f7b9944cc3835cce0de574c6f1c226728c7e81%不明1
29claude-sonnet-5 eqbench-creative-writing-v3:claude-sonnet-5config_21177d7527595df7daa466aaaa2b626fef884959fb02fbe0a0ce29246569437081%不明1
30space-bunny-alpha eqbench-creative-writing-v3:space-bunny-alphaconfig_b1f32cd42070945ec9b7872ba2da07a595bbeca9cd3420332b353a575393a78e80%不明1
31zai-org/GLM-5.2 eqbench-creative-writing-v3:zai-org/GLM-5.2config_2183d121cbdfe1083c1d2d83c32984b2c54ca59629cd8d1162439a84bd4b2ecc79%不明1
32gemini-4-argon eqbench-creative-writing-v3:gemini-4-argonconfig_594e13bd1d24dc1d17e0985fa2095476b2951f1aa28892255d5bd4df3b5b854779%不明1
33gemini-3.8-flash eqbench-creative-writing-v3:gemini-3.8-flashconfig_150a025d810fa77d9af0b6007ff1d91200a130ed4edae0fd8605e228879cce0578%不明1
34moonshotai/Kimi-K2.6 eqbench-creative-writing-v3:moonshotai/Kimi-K2.6config_a58c7f8ebcd24e5bbc05dfbf00d76b2b286ec9efc0181761794b01a25d9aad5077%不明1
35gemini-3.7-flash eqbench-creative-writing-v3:gemini-3.7-flashconfig_25ddae9e165a988428aa0b31990658c457a1779cb1bcbf1cc8b74e3dd2ec3fc577%不明1
36gpt-5.2 eqbench-creative-writing-v3:gpt-5.2config_e50a9e7801b60c188536626730f2f63da19cc558e526de27446eff8fc4d2aec476%不明1
37nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 eqbench-creative-writing-v3:nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4config_c6465c255eb78c0b9dc6573e00d9c21972c6778b2ae752511db4eb94aa90e42575%不明1
38gpt-5.3-chat eqbench-creative-writing-v3:gpt-5.3-chatconfig_932ecfc7ecafd7a7750680333a7c02c2e2f2c0809123be906358173324bcf97e75%不明1
39claude-opus-4-5-20251101 eqbench-creative-writing-v3:claude-opus-4-5-20251101config_3aca3db3c75525bd48891eabcfcfe4cc9a045fe5e51f0726a44581e849c16b9875%不明1
40claude-sonnet-4.5 eqbench-creative-writing-v3:claude-sonnet-4.5config_a6e0964be5d23726c44cb242daadc561428a747ede6a7bd9384528c08b448a8575%不明1
41o3 eqbench-creative-writing-v3:o3config_cd85e6a27ba8f16813ada265d28e1fe51d4cc3d01d2b45dc956c18172a551db175%不明1
42Qwen/Qwen3.8-27B eqbench-creative-writing-v3:Qwen/Qwen3.8-27Bconfig_200bdc3c7c0c63bf29caa15e97f7d15248382a37c10d5f83ed6b35b925787b7974%不明1
43moonshotai/Kimi-K2-Instruct eqbench-creative-writing-v3:moonshotai/Kimi-K2-Instructconfig_463cede625c746d8ec094207fa2df42e4f00ab98674a840ceb7cf618b98f773974%不明1
44gpt-5.4-mini eqbench-creative-writing-v3:gpt-5.4-miniconfig_fc73b8091253ec99e32675351d9f367365bd8920599859819d6c7f2eee8bd63e74%不明1
45moonshotai/Kimi-K2-Thinking eqbench-creative-writing-v3:moonshotai/Kimi-K2-Thinkingconfig_e0902b7586095a05e2137b4cfb7aad52765aa7961ef5c27ed8c7eac401a2e73872%不明1
46openrouter/horizon-beta eqbench-creative-writing-v3:openrouter/horizon-betaconfig_44da302616c8fa0ba0571ee2a11135d82bac31967cde69029f7ba40c55ccb12d72%不明1
47gpt-5-2025-08-07 eqbench-creative-writing-v3:gpt-5-2025-08-07config_ada5d5552fabf3b2f39abc2755f0305aa824bce375ccdd0a9d7dec27a862969772%不明1
48openrouter/horizon-alpha eqbench-creative-writing-v3:openrouter/horizon-alphaconfig_31ac4c3705ca0bcf3c6a5fd335ec272e3775ea0b67ff02ec7e14a2e51f8c333672%不明1
49openrouter/pony-alpha eqbench-creative-writing-v3:openrouter/pony-alphaconfig_af736def195b82dee4b190f221c1bd53abd33d585b0fe41a2b96b0345b7efa8d72%不明1
50thinkingmachines/Inkling eqbench-creative-writing-v3:thinkingmachines/Inklingconfig_5f56bc09fb3614ba34ec29572cd0852a7c8cb50f1288f28c366ce3de9380852971%不明1
51gemini-3.6-flash eqbench-creative-writing-v3:gemini-3.6-flashconfig_b97f34e42c3f85a33bd7d8a1c0b079c6dedc79e974fc51989ba25a916f782f8f71%不明1
52zai-org/GLM-5 eqbench-creative-writing-v3:zai-org/GLM-5config_deb6cf61aa7e18fe54e27230a136298c224d3fc99209c4eb6d9284aaae81eebd71%不明1
53zai-org/GLM-5.1 eqbench-creative-writing-v3:zai-org/GLM-5.1config_312f70bce81a9a6476865759d5e94976a65229fcf23c29ee5bc943b83ea96d8e71%不明1
54AlexWortega/Qwen3.8-27B-antislop eqbench-creative-writing-v3:AlexWortega/Qwen3.8-27B-antislopconfig_9552a0fb53fcb7afddd97c12a93980637f31e9894df3ba912da1bd7e7944f4a370%不明1
55moonshotai/Kimi-K2.5 eqbench-creative-writing-v3:moonshotai/Kimi-K2.5config_d654830bbc843521c8fd262a6de2f1fc464c7d55586f66839bc4c085e4cb128f70%不明1
56claude-opus-4 eqbench-creative-writing-v3:claude-opus-4config_36666edc2a7289d597f2ab890aebaa13598993f7af2003c28d9dc5045c7055b270%不明1
57grok-4.5 eqbench-creative-writing-v3:grok-4.5config_f6bc46fa147cb6f6b9a67207d6897da9312ec39c66ddfa53a122fcc220190b9e70%不明1
58grok-4.20-beta eqbench-creative-writing-v3:grok-4.20-betaconfig_25744d08fba6b5b8bf756236941c805792ca987ced328148feac95110372602a69%不明1
59deepseek-ai/DeepSeek-V4-Flash eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V4-Flashconfig_679cdf0b1260d3f0a27136164b81aae18624338587f00837f25ff2536020eda369%不明1
60gemini-3.5-flash-lite eqbench-creative-writing-v3:gemini-3.5-flash-liteconfig_5598e3816326dae1b7a5147ddab645d9ff756dcf9e9ee70a19fa786dbc0ff7ae69%不明1
61deepseek-ai/DeepSeek-V4-Pro eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V4-Proconfig_4efe59ffbde0e9b985d3c3985d08dae8587e120e5dacd15a82d094b81eb5145a68%不明1
62deepseek-v4.1-flash eqbench-creative-writing-v3:deepseek-v4.1-flashconfig_e240aa5182e9c1a4acf9a376c30c46680e86b5f3a53048e48e94c361241814a868%不明1
63gemini-3-pro-preview eqbench-creative-writing-v3:gemini-3-pro-previewconfig_c3514a9bf1d2b33bdec1231a046c8c0c817149674f9e25adcd9ccaf771136e4567%不明1
64deepseek-ai/DeepSeek-V3.2 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V3.2config_dc73e5f7789cf58d737ba072bd646547334947b5a0bdffcb17060eaa1cec62ae67%不明1
65chatgpt-4o-latest-2025-03-27 eqbench-creative-writing-v3:chatgpt-4o-latest-2025-03-27config_9ec56f17c630bab0e32201cebf0c40064352bd234ab7b24ef15ae769bff9c3db66%不明1
66deepseek-ai/DeepSeek-R1 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-R1config_e071a4bbf347d1a3af61812500d53951f6b32680321383fec368a197c59dc26366%不明1
67XiaomiMiMo/MiMo-V2.5-Pro eqbench-creative-writing-v3:XiaomiMiMo/MiMo-V2.5-Proconfig_d59d3b1a505d2056dd5de6c2964f50041b0e2535527c8256f8f5dcf51a74c63d65%不明1
68thinkingmachines/Inkling-Small eqbench-creative-writing-v3:thinkingmachines/Inkling-Smallconfig_532523066cee979041c6f9628001fdd40aa604d92a31ff68c5e3c9568bfce6ab65%不明1
69gemini-3.1-pro-preview eqbench-creative-writing-v3:gemini-3.1-pro-previewconfig_c412aabd593317d9010206701560ef0c0976c358de213709f515602a15e66d9365%不明1
70hunter-alpha eqbench-creative-writing-v3:hunter-alphaconfig_8e79ac2e178bed87362ed8f33a541fc096cd9155dfe4b9507ed3d508b046d62865%不明1
71claude-sonnet-4 eqbench-creative-writing-v3:claude-sonnet-4config_9891b4a49393b2d9d88ae796dcc7880e8766c38de03c214c47aa3962e53372de65%不明1
72Qwen/Qwen3.5-397B-A17B eqbench-creative-writing-v3:Qwen/Qwen3.5-397B-A17Bconfig_71745749b4d02fbdc27900c8c517ca0387de7f8f9eef91fd50ce9fa779bd596a65%不明1
73mistral-medium-3.1 eqbench-creative-writing-v3:mistral-medium-3.1config_06066befb46f3ed70dd6a0120ff7e92b2094827ca9383c2efdf97550a38e733865%不明1
74deepseek-ai/DeepSeek-V3-0324 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V3-0324config_abfa51d2d7b26126dea380682e61713f7a2782ef1b0d768e1389cd04f8d7837764%不明1
75claude-3-5-sonnet-20241022 eqbench-creative-writing-v3:claude-3-5-sonnet-20241022config_66047ff4b3cd66d3b02c3bf53d613d6d979fe3299c26afbc304f5760d1046e0763%不明1
76deepseek-ai/DeepSeek-V4-Flash-0731 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V4-Flash-0731config_3627a40768f71f22c6779f8a2fb612161c422eb8b57b18ef8de1d2f24206b12363%不明1
77deepseek-ai/DeepSeek-V3.1 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V3.1config_0643eb00b2d177d5288ceac54d1f5639230779b8dd310fb5d646ce1bea85940f63%不明1
78gemini-2.5-pro-preview-06-05 eqbench-creative-writing-v3:gemini-2.5-pro-preview-06-05config_37437e1c59557c92534b07ae0c0a0f5c22b7562aa71763b55b4c00160ccfed2462%不明1
79deepseek-ai/DeepSeek-R1-0528 eqbench-creative-writing-v3:deepseek-ai/DeepSeek-R1-0528config_b37287b0220fcebe5241bc294f4eeda3ff33c0173078b944808c676862b3524f62%不明1
80NousResearch/Hermes-4-405B eqbench-creative-writing-v3:NousResearch/Hermes-4-405Bconfig_326d2285e7a88d5e197634a4e8a99db1a5898d4bfda2a3456da800e31c4fa48162%不明1
81gpt-4.1 eqbench-creative-writing-v3:gpt-4.1config_a619bb399cbd81b65c9e887e78a324e69b5475d39eb5bf3bb3b5b57952b24d3762%不明1
82optimus-alpha eqbench-creative-writing-v3:optimus-alphaconfig_481fc6efd27fdde47e60144d363e11aae11dfb1f92ab9745555ea8fbb6ee848e62%不明1
83zai-org/GLM-4.7 eqbench-creative-writing-v3:zai-org/GLM-4.7config_f835d0573d4c3dd365d8a1cf0f33574342da75555fe23b95a9fcb3b8263581dc61%不明1
84mistralai/Mistral-Large-3-675B-Instruct-2512 eqbench-creative-writing-v3:mistralai/Mistral-Large-3-675B-Instruct-2512config_62befed38d8f4045565444b0d5840c3b8c7655c14858a8c799846f149ca951c961%不明1
85claude-3-7-sonnet-20250219 eqbench-creative-writing-v3:claude-3-7-sonnet-20250219config_4ac989e40eb5f922f7c6cc94a997cd16fbcf2c58795dad1f8a90244438ea8e0761%不明1
86zai-org/GLM-4.6 eqbench-creative-writing-v3:zai-org/GLM-4.6config_36e0763938d12192367deeb109ab6ebd56ad7fa859504254abb697222d8372df61%不明1
87gemini-2.5-pro-exp-03-25 eqbench-creative-writing-v3:gemini-2.5-pro-exp-03-25config_fee09b1964eb19b07fcdd80958b78c897f739bbd696792c73e1b637f99143b2d61%不明1
88mistral-small-creative eqbench-creative-writing-v3:mistral-small-creativeconfig_6d36075b518eb94f3b059ff00ea8a9b32d340fae338d095555d215bac0cc716059%不明1
89google/gemma-4-31B-it eqbench-creative-writing-v3:google/gemma-4-31B-itconfig_99b35733f3a35623d40b08c6107777e29afa3d578568796a884a9ed1194a95d759%不明1
90qwen/qwen3-235b-a22b:thinking eqbench-creative-writing-v3:qwen/qwen3-235b-a22b:thinkingconfig_adc1fd3e8293d1f876e049064ed44fb3fb6184b89c87d8be448719b4f4e856bd59%不明1
91minimax/minimax-m2.5 eqbench-creative-writing-v3:minimax/minimax-m2.5config_70503f51b60da468106161a5b39510fa1c53a31561b2688f750fa1667799023959%不明1
92quasar-alpha eqbench-creative-writing-v3:quasar-alphaconfig_76ded4f0d4490cd9ce953d6ee37a7951ba980b4d69b8c481cae3f0c27ed08f3058%不明1
93chatgpt-4o-latest-2025-01-29 eqbench-creative-writing-v3:chatgpt-4o-latest-2025-01-29config_d8f10144235de8c4210b18ff7b6e87a55367c0252fbe7acaf6535f2c1613785e58%不明1
94zai-org/GLM-4.5 eqbench-creative-writing-v3:zai-org/GLM-4.5config_3f19889c9a1359073cc05074b97c3df8341dcde9f528ea80d8a67d445ae22a5558%不明1
95openrouter/sherlock-dash-alpha eqbench-creative-writing-v3:openrouter/sherlock-dash-alphaconfig_6c4cef4586803424ebce85b8f9d26e38fa29be88389db9d9ba161efac9cfa72b57%不明1
96grok-4.1-fast eqbench-creative-writing-v3:grok-4.1-fastconfig_93e06258041b4ca25852ff7154c5fcda072bcf546da877ce4a1140ddab08a34557%不明1
97gpt-5-mini-2025-08-07 eqbench-creative-writing-v3:gpt-5-mini-2025-08-07config_cd3b1ee22371eec061c2e058d434d9b37d82ae32a32e6f47d0885b9994a422b556%不明1
98google/gemma-4-26B-A4B-it eqbench-creative-writing-v3:google/gemma-4-26B-A4B-itconfig_a080292f8ede9c6dc86297e2ec4b327dd7ae334386f676b7b8cf4af9222097a156%不明1
99google/gemma-4-12B-it eqbench-creative-writing-v3:google/gemma-4-12B-itconfig_3cf3f7b04b327f033c399969d93b5cc86c0e3092abc8870343af0be88bf6369555%不明1
100nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 eqbench-creative-writing-v3:nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4config_04863819e8e15eb2da21392cb85deea93900d211ea70525fb71a58d1aac2b03c55%不明1
101deepseek-ai/DeepSeek-V3.2-Speciale eqbench-creative-writing-v3:deepseek-ai/DeepSeek-V3.2-Specialeconfig_88acdf127be991dcb46c92015a63c1f86a2999b0f45cbc37d6a1c79a4f5fe74854%不明1
102google/gemma-3-27b-it eqbench-creative-writing-v3:google/gemma-3-27b-itconfig_3a019358ef10fa68a3230a68250d448bf2b6da853165625b2d4b21e89e1a7a4f54%不明1
103gpt-4.5-preview eqbench-creative-writing-v3:gpt-4.5-previewconfig_a96fac514605993663ea3de67863c030957f24dfcd18505614f2ab88358d589354%不明1
104qwen/qwq-32b eqbench-creative-writing-v3:qwen/qwq-32bconfig_ddac4ab9fc39243d1944b26f43fa152cf4b79e41ebc877753d3aa9281683fecb54%不明1
105mistralai/Mistral-Small-3.2-24B-Instruct-2506 eqbench-creative-writing-v3:mistralai/Mistral-Small-3.2-24B-Instruct-2506config_cc1d3fe2c604ba29ef55aa927518887fb70c6a10b8366585b973c42eb3d43f0553%不明1
106RekaAI/reka-flash-3 eqbench-creative-writing-v3:RekaAI/reka-flash-3config_1295c672023b7bde52b0df12e110f60eed996af6b2c7b6ed839714729a2021a152%不明1
107grok-3-beta eqbench-creative-writing-v3:grok-3-betaconfig_91f6b88710b631f6694c8c32f0e9b78806061d3f2f118f700ba48aece0298c3d50%不明1
108gpt-4.1-mini eqbench-creative-writing-v3:gpt-4.1-miniconfig_4f36b6d51ad8510d7dbd49624f288a7592f640a04887e031dc7f55169a7ebac248%不明1
109CohereForAI/c4ai-command-a-03-2025 eqbench-creative-writing-v3:CohereForAI/c4ai-command-a-03-2025config_afa2df6a530c9b98ebc51ce5c60d9bea9cb6853bc16397e5b65f098a61b4a39848%不明1
110anthropic/claude-3.5-haiku-20241022 eqbench-creative-writing-v3:anthropic/claude-3.5-haiku-20241022config_3971341671a62f1f4dfaae70d6a1dbd36297b3824b451f1dddd900ea68bfa51048%不明1
111zai-org/GLM-4.7-Flash eqbench-creative-writing-v3:zai-org/GLM-4.7-Flashconfig_c697368b5cfa0160ceac551a83340c3708a280b29e4e57cc29ea9a55abb8675e47%不明1
112gemini-2.5-flash-preview eqbench-creative-writing-v3:gemini-2.5-flash-previewconfig_4d2a15acc4c350e6e758e33c85d7e8a6f0025433368566b13f8869f0c23b1c2947%不明1
113allura-org/Gemma-3-Glitter-12B eqbench-creative-writing-v3:allura-org/Gemma-3-Glitter-12Bconfig_e7d5db3c36b5cdd7937e15a52d66fd84f08f434250b833fd5ff1c567ab99f60547%不明1
114google/gemma-3-12b-it eqbench-creative-writing-v3:google/gemma-3-12b-itconfig_02de0da09ddada714a70ed9be3aec75d7ac5e72c648ff621cedbaa445ffa214047%不明1
115gemini-2.0-flash-001 eqbench-creative-writing-v3:gemini-2.0-flash-001config_e2a797f475d7ea0c5070b59fa701f217ed173a841654d841228cb56b6441904547%不明1
116google/gemma-4-E4B-it eqbench-creative-writing-v3:google/gemma-4-E4B-itconfig_c45cde241969e8fb4fb0bc7a62ac0c1caab7efa111fef859ea9ad863da58b3e245%不明1
117nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16 eqbench-creative-writing-v3:nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-BF16config_f1edde1d3e888aa338dbcb973ce098911e6785596b997f2435d351f26b28256d45%不明1
118sam-paech/Darkest-muse-v1 eqbench-creative-writing-v3:sam-paech/Darkest-muse-v1config_e3855fe5099b77369e614c5c9f3ef378ea523a43a7b886a7b11092fabfb696ec45%不明1
119THUDM/GLM-4-32B-0414 eqbench-creative-writing-v3:THUDM/GLM-4-32B-0414config_d9153f946a19a1bf213d1c78a0a68a79066b7ddc3eaecad02702b76a6719f4c344%不明1
120google/gemma-3-4b-it eqbench-creative-writing-v3:google/gemma-3-4b-itconfig_38ce05020ab120a9b26069985ffe73a98521fc2c5eaef7a80527e40e2c6061ac44%不明1
121mistralai/Pixtral-Large-Instruct-2411 eqbench-creative-writing-v3:mistralai/Pixtral-Large-Instruct-2411config_4da5d0f85c8eb1ef3e41f173eb813e28adf7e7cf31853f1d721596f79a34cd6340%不明1
122ifable/gemma-2-Ifable-9B eqbench-creative-writing-v3:ifable/gemma-2-Ifable-9Bconfig_ff7d927b99ff60502f3d711a5d3e22d9f28d7317568ae761159d350feb7dc89440%不明1
123mistralai/mistral-large-2411 eqbench-creative-writing-v3:mistralai/mistral-large-2411config_87e680b4a4fc6f09002beee3671f83ad1d0453dc2e530801a2118f2f7a032c5d40%不明1
124openai/gpt-oss-120b eqbench-creative-writing-v3:openai/gpt-oss-120bconfig_88514aaeca4c166d99ce7edf71943d24d0d92cb7e5bd9beb543987ef46ca094a38%不明1
125gpt-4.1-nano eqbench-creative-writing-v3:gpt-4.1-nanoconfig_a1d35f1ad18cd89023b47af7a8126289ae4e8b78a527f9ffc4df4915609e200c37%不明1
126ToastyPigeon/Gemma-3-Starshine-12B eqbench-creative-writing-v3:ToastyPigeon/Gemma-3-Starshine-12Bconfig_a8b055536ae290412fab9e70d09eaece44501b6cdfadec129e86b61220c5049834%不明1
127mistralai/Mistral-Nemo-Instruct-2407 eqbench-creative-writing-v3:mistralai/Mistral-Nemo-Instruct-2407config_5775343f54ca03498ab8e0db39e2dbbda2fe2225398a07c01490ded7374c8ed234%不明1
128gpt-4o-mini eqbench-creative-writing-v3:gpt-4o-miniconfig_255d25107ec1c796a470be8be08c46ce16ffca6beddeb9f476e48f544db2482334%不明1
129meta-llama/llama-3.1-405b-instruct eqbench-creative-writing-v3:meta-llama/llama-3.1-405b-instructconfig_aac1cbaee39c0654cde31a7f1256241f9b95b993e31029aa3cb6e1241553feee34%不明1
130meta-llama/Llama-4-Maverick-17B-128E-Instruct eqbench-creative-writing-v3:meta-llama/Llama-4-Maverick-17B-128E-Instructconfig_28744f9ca74d2c7ba484a32f3ef102bfad33c622146be1ac147f5bed85acdd4433%不明1
131google/gemma-2-9b-it eqbench-creative-writing-v3:google/gemma-2-9b-itconfig_160993a24295e3fb00e72d1d4da074bbeb1ec6723106d993246bcb36510008f532%不明1
132Nanbeige/Nanbeige4-3B-Thinking-2511 eqbench-creative-writing-v3:Nanbeige/Nanbeige4-3B-Thinking-2511config_2267499254e060b0e95d4e8de3267f7f813d6b23a009d1bb5847b8346669caee32%不明1
133meta-llama/llama-3.1-70b-instruct eqbench-creative-writing-v3:meta-llama/llama-3.1-70b-instructconfig_7e31d46b6c09f818a8558f3ca679899268a202207e9ab7c500ca85deb1e8446329%不明1
134meta-llama/Llama-4-Scout-17B-16E-Instruct eqbench-creative-writing-v3:meta-llama/Llama-4-Scout-17B-16E-Instructconfig_0e14718366a0243c1944465f19a6019213e18bd156d358351147be0ad14288f329%不明1
135openrouter/cypher-alpha eqbench-creative-writing-v3:openrouter/cypher-alphaconfig_52f1d23562065be2cbde8c2e4f7e2bdb3a93ee7d423e5943cc8b6c936fe0abec29%不明1
136mistralai/mistral-small-3.1-24b-instruct-2503 eqbench-creative-writing-v3:mistralai/mistral-small-3.1-24b-instruct-2503config_7b06931ccd8d20a89f90e323ce6b26f82d69d335948716589648c14710d23da728%不明1
137openai/gpt-4-0314 eqbench-creative-writing-v3:openai/gpt-4-0314config_6cbd5398cec5ed8f91fbad584dc5e933827103fe322329f570d59d449a7757c628%不明1
138liquid/lfm-7b eqbench-creative-writing-v3:liquid/lfm-7bconfig_66f194ed18f288b2511103d52740d2467695fac6530e8edf41b635fb29a19ec328%不明1
139anthropic/claude-3-haiku eqbench-creative-writing-v3:anthropic/claude-3-haikuconfig_e12df3fcb06cd2f5d849bbfd13324e9672884013757fecf881d86ec8c624a6b926%不明1
140meta-llama/llama-3.1-8b-instruct eqbench-creative-writing-v3:meta-llama/llama-3.1-8b-instructconfig_62465fca2daaffa2df5c23f76a70b76db52c12873b53fe604d6e4326ccbd89ce26%不明1
141mistralai/Mistral-Small-24B-Instruct-2501 eqbench-creative-writing-v3:mistralai/Mistral-Small-24B-Instruct-2501config_eedceada642ccbbe954f056b22ebc92da482ef113b77345b13e63e8445b9469226%不明1
142gpt-5-nano-2025-08-07 eqbench-creative-writing-v3:gpt-5-nano-2025-08-07config_f528bfa90e1af731c81d840b630b3da1e55189feb5732fe0b90cc02660b7d1b725%不明1
143openai/gpt-oss-20b eqbench-creative-writing-v3:openai/gpt-oss-20bconfig_82a6225c16687dcc5591e0080d36dd0b0de2191d4cb3595b765e436c8ee7d0e423%不明1
144meta-llama/llama-3.2-3b-instruct eqbench-creative-writing-v3:meta-llama/llama-3.2-3b-instructconfig_d801452bbb8188271e92d3638970ff23b539786295235e4897e3c9ba7babcaf520%不明1
145openai/gpt-3.5-turbo-0613 eqbench-creative-writing-v3:openai/gpt-3.5-turbo-0613config_f1e9b4eecc08af220ffed24f9c925fd4bd19e8fa7a183dda2838256f0573b60113%不明1
146meta-llama/llama-3.2-1b-instruct eqbench-creative-writing-v3:meta-llama/llama-3.2-1b-instructconfig_f01a5702e77167e184c06e97c1156079792922cab3614965286d06c8742dc6770%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