Coding (frontend)

结果只在同一分组内进行比较,因此用一种方式测试的模型绝不会与用另一种方式测试的模型同榜排名。

Rank models and agents on building and iterating web interfaces from a specification

各排名分组使用独立的评分尺度。请只在同一分组内比较配置;EvalRank 绝不会把不同的系统压平到同一个榜单上。

跨基准共识

把该主题下已收录的基准合并成一份模型排名,权重与实际决策时一致。每个分数代表该模型成绩占最佳成绩的比例。

排名模型最佳占比基准测试
1mimov26flash100.0%1
2hy4preview99.6%1
3qwen38flashnext99.5%1
4mimov26pro99.3%1
5glm53flash98.1%1
6qwen3827b97.1%1
7minimaxm31flash96.7%1
8Claude Opus 4.795.0%1
9grok4594.9%1
10mistrallarge494.3%1
11musespark1194.2%1
12Claude Opus 4.693.9%1
13Claude Opus 4.893.8%1
14claudesonnet4693.0%1
15seed21propreview92.8%1
16Qwen3.7-Max92.5%1
17kimik2692.2%1
18glm5192.1%1
19hy392.0%1
20Gemini 3.5 Flash91.0%1
21minimaxm390.6%1
22sparkx2690.5%1
23qwen36maxpreview90.5%1
24mimov25pro90.4%1
25kimik27code90.0%1
26Claude Opus 4.589.7%1
27qwen36plus89.3%1
28gpt55codexharness88.9%1
29DeepSeek-V4-Pro88.4%1
30gemini31propreview88.4%1
31gpt54codexharness88.2%1
32Gemini 3 Flash88.0%1
33gemini3pro88.0%1
34mimov2587.9%1
35Kimi K2.587.7%1
36beam10501ba23b87.7%1
37glm587.7%1
38glm4787.7%1
39mimov2pro87.6%1
40gemini35flashlite87.6%1
41GPT-586.6%1
42gpt5286.5%1
43inkling86.4%1
44inklingsmall86.1%1
45kimik25instant85.9%1
46GPT-5.485.6%1
47glm5vturbo85.6%1
48qwen35397ba17b85.5%1
49nvidianemotron35supervl120ba12bnvfp485.5%1
50minimaxm2785.4%1
51GPT-5.185.2%1
52Claude Opus 4.184.9%1
53minimaxm2584.7%1
54Claude Sonnet 4.584.6%1
55minimaxm21preview84.5%1
56Grok 4.20 Beta84.0%1
57solarpro483.7%1
58gemma431b83.6%1
59qwen35122ba10b83.1%1
60gemma426ba4b83.0%1
61qwen3527b83.0%1
62grok4382.9%1
63hy3preview82.9%1
64museglimmer82.8%1
65lagunam182.4%1
66glm4681.9%1
67gpt52codex81.8%1
68gpt51codex81.7%1
69Claude Haiku 4.581.3%1
70kimik2thinkingturbo80.7%1
71lagunaxs279.6%1
72minimaxm279.2%1
73MiMo-V2-Flash78.9%1
74qwen3coder480ba35binstruct77.9%1
75deepseekv32exp77.7%1
76mistralmedium3577.2%1
77gemini31flashlitepreview76.7%1
78katcoderprov176.7%1
79qwen3535ba3b76.6%1
80qwen35flash76.0%1
81gpt51codexmini76.0%1
82Grok 4.1 Fast75.9%1
83trinitylargethinking75.6%1
84mistrallarge375.3%1
85gemini25pro74.9%1
86Grok 4.174.2%1
87devstral273.1%1
88granite418b72.8%1
89mercury271.5%1
90grokcodefast171.2%1
91Grok 4 Fast70.8%1
92Devstral Medium65.4%1

竞技场系统 · 众包两两对比

探索性——尚未产生排名冠军
rg-coding-frontend-arena-system-crowd-pairwise-arena-system-v1

Explorer 依据

WebDev Arena

单一来源。观测于 ;有效至 。

排名配置能力不确定性家族
1Claude Opus 5.5 (Max) 2026-10-28config_084599a275e2ecc33b392f6b21b473b3099ce15e9f548adf538f09167cd57b67100%未知1
2GPT-6 Astra (Max) 2026-10-28config_51830a6371ffd7ce2aaf4132cd8265e5dfa55cfebbd3512026ebe097defea97995%未知1
3Claude Sonnet 5.5 (xHigh) 2026-10-28config_b566020b60b6f84a037865ec779e73f2745ee7f18eb149cb3fdd045e9ace80c595%未知1
4Gemini 4 Carbon (High) 2026-10-28config_b5885d0c4371c65bfa5847c537c31c7833df2e3a5f9c88dcbd86ca74a5e4dbba94%未知1
5GPT-6.1 Sol (Max) 2026-10-28config_ffacb76a2986667bcda568d04996bdf1e906a794075aa9a5f15db7a272cde56992%未知1
6Claude Fable 5.1 (Max) 2026-10-28config_bd097b8d37cd0bd6889953b471a7374526f39306101b84ab14cf2a5a97142dd491%未知1
7Muse Wonder Full (Max) 2026-10-28config_d935215235a69c6a8870fd51180b96d36988a550f9073761f04c0327904f15b589%未知1
8Claude Sonnet 5.5 (High) 2026-10-28config_c50afdf1ac1726362497edd399c214c5b94210dc9f184fea660a6e85fe19de3387%未知1
9Kimi K3.1 Pro (Max) 2026-10-28config_9a6cf0c4808e4dafde0c0f76ad266ad50c6c44590b1ba408e9f4ad2b718f4ebe84%未知1
10Claude Opus 5 (Max) 2026-10-28config_1e58c5f3745e8b97d9407c7d53132b338dad140fd249fd2d57561fc8034d335484%未知1
11Gemini 4 Argon (High) 2026-10-28config_6432998da74ca18daed355f209e566e8d01dcf3d0811d4582df594ba308e03be82%未知1
12GPT-6 Sol (Max) 2026-10-28config_bb31f3c169d756fa12582e0d16d19c9a1df889b0477bc261ba258b2053281d8b82%未知1
13Qwen3.8-Max (0902) 2026-10-28config_3764034f83f951a7a778d8061aa231c05b829ba8ea5c814b93e0d1dc98af03c182%未知1
14GPT-6.1 Terra (Max) 2026-10-28config_6e038f6481b3f31fecfabca695a00f623f0c36bf037d01ab933de16c4849c57e81%未知1
15Qwen3.8-Max 2026-10-28config_5d1f9f2850baa283cf067db9e43b5258529fc41cdd642d4eb0633c2f9f64d35081%未知1
16DeepSeek-V4.1-Flash-20261017 (Max) 2026-10-28config_e606b306bd4d361da1bb0795f652b327407c6e332a634fbf942eaf2b5eace8ce80%未知1
17Claude Opus 5 (High) 2026-10-28config_b46e989a33026b7201ab0e25f73f1bab48bef0058b9baded39db0fe6613ba4bf79%未知1
18Kimi K3 (Max) 2026-10-28config_0b7ded79e4b765c6180aae8a37fd472c676d7686bc733999b6cb6bcffed276b579%未知1
19Muse Spark 1.3 (Max) 2026-10-28config_e472fb7e89171e0551becbbdcd5315969c25419ec8f47f83d56c3201f18cd82579%未知1
20Muse Wonder (Max) 2026-10-28config_1b39a10afde9161478e6bedc63e6589d4cd3693e6a296e8d3734842652d0107e79%未知1
21Grok 4.7 (xHigh) 2026-10-28config_919a0fb21822b7fe4118472e6be38a3fd3e89cec9c523b133c507f21f76b483277%未知1
22MiMo-V2.6-Flash 2026-10-28config_efb00ed12debed0e7d64d768b27731e7c599e17ccc4a4d856b77883e43095e8b77%未知1
23Hy4 preview 2026-10-28config_7c3d10207795fff35f3d4a457a0c5e173d53b6195a0fa515789c02efedffa21676%未知1
24Qwen3.8-Flash-Next 2026-10-28config_b218123a96fc95641c70960b3d516813bfdc9bdd7ee79acd4fafb6e1c2057a5f75%未知1
25MiMo-V2.6-Pro 2026-10-28config_a90bfe5f4a8e6813e428e8e39f946d8952a0aefc0955ed74014ebf0edaad4b3175%未知1
26Claude Fable 5 (High) 2026-10-28config_2a73253495da68dd0fa25050a9742de1a851a2d17a8936e71a7af383a571ff5575%未知1
27GLM-5.3 (Max) 2026-10-28config_6d1ef09daa9541e21f0e2d48ebf5c60516c0128797e2c7dbd46636b420e9b20a75%未知1
28Muse Spark 1.3 (xHigh) 2026-10-28config_46ceae567d6575fc78fdf1a8027aee115ccf3e0e7ee33bf5cbab5856500445c874%未知1
29DeepSeek-V4.1-Flash-20260910 (Max) 2026-10-28config_da6c8def458ed53d2e549a914f3d94d3a464df6033847bc54e9031cce7d6d04c74%未知1
30Grok 4.6 (High) 2026-10-28config_b1df94ccc507313b4046e201b43ed98dfa78ed94d4d8b2340610aba8b0759f3474%未知1
31GPT-5.6 Sol (xHigh, Codex Harness) 2026-10-28config_3c9a490032ebda40472a4ad10859c7e0a71ea1d54b2da15e5a3e22f9e2cef7e174%未知1
32GLM-5.3-Flash 2026-10-28config_89ddbe2417e2a7b6eed655ea7c11869f5fb3cd7cfb9236eb4478a6510dfe194572%未知1
33GLM-5.2 (Max) 2026-10-28config_1c067e34d8425eca81e276822bddb10b98f8c46855f4d7865df23ba7e46c397d72%未知1
34Qwen3.8-27B 2026-10-28config_c1a6506519a672db95df472125ae2f25c30cb9a89e6618e8f618679bccf7d39570%未知1
35Gemini 3.7 Flash (High) 2026-10-28config_9db5e2752ade2872af93694d3449028b62cdb7a5d15beac2d998b590e16a4c5570%未知1
36Claude Haiku 5.5 (High) 2026-10-28config_303cacd37229916aca42b1fe17583bcd35fdc673056f2210bb70fe54eed26c3770%未知1
37Gemini 3.8 Flash (High) 2026-10-28config_3652be9953d261d0050fb0995a1591ec590059df8fa5a73bbf30205c207bea2e69%未知1
38MiniMax-M3.1-Flash 2026-10-28config_aae5cd8ca2cceb3559c0e94a729b101533c7c41abac0b6bd8c1f42b81a0a3d4269%未知1
39DeepSeek-V4-Pro (High, 20260813) 2026-10-28config_0b05f128d7a755dee259972d7da44d4fafd72bff6a44be7161b08b6e34860d6e69%未知1
40DeepSeek-V4-Flash (High) 2026-10-28config_8179bfb73cff50fbc85446cfeb2c853900a190b0d8cbfc1fe03f3d3c249569fb69%未知1
41GPT-6 Luna (Max) 2026-10-28config_0d0acb55cfa859062104ea03d70e02d556c74c0f61f5f1f84b2d9d523357413769%未知1
42Step 5 Preview (High) 2026-10-28config_5a7b7269210d74b8d558d4408cb9143ca73d6780513d8ba57aa8e373eab7082f68%未知1
43Claude Opus 4.7 (High) 2026-10-28config_a0893952f903309f38846f36b00231417668a2a4a891e2477648c3de6c45e70e66%未知1
44Claude Opus 4.8 (High) 2026-10-28config_7d7f2728fe3a8022b3b3376cd4756483d70fb0835c93ae2476ac9621f4b20e6566%未知1
45Claude Opus 4.7 2026-10-28config_f6c7e371219a6d99e803f9396c66f2626b12ac473b7c243321fa2c843813cacc66%未知1
46Grok 4.5 2026-10-28config_a0ffd6609260d519939ed3c533540f5778ab3dbbfaec582e241e07c56021c3d565%未知1
47Claude Opus 4.6 (High) 2026-10-28config_71b3bad3c7d123207dc57d3ac4c4343e9ca0a2857ac27ac24576d820749c562764%未知1
48Mistral Large 4 2026-10-28config_2a06cd32756758c970720a67b63a99c63446d8c4acaef7e67fc87bbfee11e24464%未知1
49Muse Spark 1.1 2026-10-28config_d4af76ee4a06e86c56cb3986c506879e5476a761a2bb84d729248567f5aec1a364%未知1
50Claude Sonnet 5 (High) 2026-10-28config_e6953c08753b928e5af7145fdd3ed3ee57c9b604244ec4547ff49c1b7be9bdc563%未知1
51Gemini 3.6 Flash (High) 2026-10-28config_54d01ce2e2f8cc1bac4e770892927598f97ff5f1540dae0135e15f88764eb42763%未知1
52Claude Opus 4.6 2026-10-28config_56ead420187d3a8a7b41a1196ee296de6df5500d1b61df5d52980ca11803df5163%未知1
53Claude Opus 4.8 2026-10-28config_4ba234aa493ae5cd6fea44ee1e421f71dd9703fcd0a57c609f05ea5fadfd41b563%未知1
54Muse Spark 1.2 (xHigh) 2026-10-28config_2885794b66bedac4effd325f8faa444f95f5ed7202e1361fa63ecc8e0910bc5663%未知1
55Muse Spark Open (Max) 2026-10-28config_50a9393101152084234988b7b6d371bf8537ef6e8b1db0b23e69029ba417093362%未知1
56Claude Sonnet 4.6 2026-10-28config_548199089e3bce2ea1fad23b707f0fbd27632542663e46558b34f8de838d4a7861%未知1
57GPT-5.6 Terra (xHigh, Codex Harness) 2026-10-28config_f3d6b5c8454dfbc0308eabfd4197f312930941106809e3a2207fcdc2640f655e61%未知1
58Seed2.1 Pro Preview 2026-10-28config_2061ddd4057137bcbba659bdd3ab7a76ae2ee7ec875667e4eb1a2460310d040361%未知1
59GPT-5.6 Luna (xHigh, Codex Harness) 2026-10-28config_78043f3b1bd3115773d2eb90686486e0644e7142a26e5161b55504a785ad2d0861%未知1
60Qwen3.7-Max (20260517) 2026-10-28config_bcf6c53f0a79b9dcde7e010b3ca8707f18e63beeb94f3fd4cf4ab744f2b41ec960%未知1
61GPT-5.5 (xHigh, Codex Harness) 2026-10-28config_70a5b942d7e40d86b3f1cdb3108eef4050d50dadb54e82affa960f3ebb4c011460%未知1
62Kimi K2.6 2026-10-28config_c6b65847fc34a26ac47dbebc5e518ceef2497c3e172406918eecb24e3551ed1759%未知1
63GLM-5.1 2026-10-28config_c3bd31b8773dec7bb6d5be4544335afa860ba332fd76a4de34f80ea032dede5059%未知1
64Hy3 2026-10-28config_a25d9e603028ed8a31501b5c8e1a4490912dac5990811c0d88255da6e940bf9059%未知1
65Gemini 3.5 Flash (High) 2026-10-28config_695672396293133a26af17b0ea320ea78772353ccfd9e56eb0f1596103a53a1b58%未知1
66Claude Opus 4.5 (High, 32K, 20251101) 2026-10-28config_c276df7ba009d3927718aa16804369178074fde0d4be596fdc3eb2a587483dff57%未知1
67Gemini 3.5 Flash (Medium) 2026-10-28config_d47df26fba1e9878228adbfb791d02dc1aa97e912e6af363c02cd22ccab91bfa57%未知1
68GPT-5.5 (High, Codex Harness) 2026-10-28config_ff25aae78aafa6a9921ab4e13dcb946a3cfab7992990491758191019640a7c5d56%未知1
69MiniMax-M3 2026-10-28config_262d41d8a151fa7ee8a19c2561ca43853c25dafa016de34d09ebca473b71006356%未知1
70Spark-X2.6 2026-10-28config_a01f5f2a24041a4e571a38949c7c210752b6ce7deb372ccc6cf65d75f5a368b456%未知1
71Qwen3.6-Max-Preview 2026-10-28config_f2071e001e4c134cdc739b6a3be4a0d2b502b56f863c0b16fa99491ce742f5d156%未知1
72MiMo-V2.5-Pro 2026-10-28config_eeea2083450257442c0275fd4794aacec120a9b9461f9a1c973346de81123b2b55%未知1
73Kimi K2.7 Code 2026-10-28config_134e208a6e6322b3ca1021f7a929e7d5bed6e65ebb5b9b13e49467aae094967254%未知1
74Claude Opus 4.5 (20251101) 2026-10-28config_1c9c88a601597e26182aa01b7cbce9f1e45e65c6ec9cf631533fc42e7eed074b54%未知1
75DeepSeek-V4-Pro Preview (High) 2026-10-28config_8ead868ac1e453f93a57b1bb21e4d5e92b356054ed87d598c0a2595a13a3b02f53%未知1
76GPT-5.4 (High, Codex Harness) 2026-10-28config_a8222bb3ea402fb009e533e2a0318193ac20d53b231852ee5b478055bd7d674453%未知1
77Qwen3.6-Plus 2026-10-28config_70ed83ae1c9d9f52b318e624ce5ab5bc31290be301afbb3e795950d1c0515d6c53%未知1
78GPT-5.5 (Codex Harness) 2026-10-28config_5018e2bfd126e6a38eee61dce0c56dac184aec9f1b559bb8ecfa51f8b95cf6c552%未知1
79DeepSeek-V4-Pro 2026-10-28config_a3f4a1cea3817823a41ac0d901563112bdd255ba9525b8777bc5f0f6a6642b8551%未知1
80Gemini 3.1 Pro Preview 2026-10-28config_98162614196039f883345c03893b46c09934bec5583988b76479f966de5996ee51%未知1
81GPT-5.4 (Medium, Codex Harness) 2026-10-28config_391927a789ad9cf0bb21aafb716eecb40c12448076b2ce63adee9dbec408fb2950%未知1
82Gemini 3 Flash 2026-10-28config_cb3964cc363adff7228a3a48b2e468e142e2daeb0e858cf52219cb017de9ed0750%未知1
83Gemini 3 Pro 2026-10-28config_b38e02e62231e15e625df727f57f79c574a41dbff08bdba8f157512c1da3728350%未知1
84MiMo-V2.5 2026-10-28config_099667268b4ff0bb2b36c92b19f65fd6bfbe4cc198d286a2013bafdfe719c38c50%未知1
85Kimi K2.5 (Thinking) 2026-10-28config_20ff5d44e0e312dbd1d86d55c67a7b1df9fd631de82eb16ca67720cfe00c973749%未知1
86Beam 1.0 501B A23B 2026-10-28config_538d31ab0def325d05a738f7c8393ab691ff712c77884ce8a8dff5163bee4c6049%未知1
87GLM-5 2026-10-28config_a728f37b4624d9eb170e19dc7e7afd20c0dfc1ad7017e680800c539029a5c8f749%未知1
88GLM-4.7 2026-10-28config_3cbac8f67d24c8fa2b4863c4102e8827c05e9504fe8135f65bca14989672d71b49%未知1
89MiMo-V2-Pro 2026-10-28config_d9d3bab83d4b223c0bde4a4003c9a05ed059c9ee2dd6c65361f6df2ab6e3e70649%未知1
90Gemini 3.5 Flash-Lite 2026-10-28config_5f2c79ba2c116b5a7148f69d9544b6d99ba53d0bf0224146a423710a428c17a149%未知1
91DeepSeek-V4-Flash Preview (High) 2026-10-28config_3b11fb309f648d3f9ed4a3a59c0a0ea31ddd7359b8f1ba987bc60a67218fa04d49%未知1
92GPT-5 (Medium) 2026-10-28config_1b53fff12c8a6033457fbda61e70e78f256fdd4065953999217685a81e3970ea47%未知1
93GPT-5.2 2026-10-28config_b50462ec90c6a2b7c3c1f0ee5bb69e0475862b559acb14a9a02bf13f1995038447%未知1
94Inkling 2026-10-28config_e6612e5cae60e38bdf5ca467aa101e87daa38ef6465ce456e2108876cbb97be647%未知1
95Inkling-Small 2026-10-28config_9c074775d10d8fdadbdccfdabe67708491e18d48e590fef83d8bf2d02a5a881846%未知1
96Kimi K2.5 (Instant) 2026-10-28config_a3735b8487d942fe5067c67c51408fbfcb925aa068795ce568da198eee8ef7f945%未知1
97GPT-5.4 2026-10-28config_f9d85f646c0a118c62dfd0862e19869e716cfe395f8cc7f138ae29c490c4d97b45%未知1
98GLM-5V-Turbo 2026-10-28config_c97363fe724129d4e908cd40c1bfc91efa6d86a3523465505bde8e89a2b2f7f345%未知1
99Qwen3.5-397B-A17B 2026-10-28config_76f6d4d75d27398a48f3b24ac013c8b991369ade3017b5719d0c522e5661cd4d45%未知1
100NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) 2026-10-28config_69357f72bc3cbdc8a058e0c1d037a720e0f96709f374dcfa8b1f0a633c7d8cfe44%未知1
101MiniMax-M2.7 2026-10-28config_44d547a42b68cf763ffab5f5846a1d7015e443c860904615f2fd846052f44fed44%未知1
102GPT-5.4 mini (High) 2026-10-28config_4daa1cbb84569c509b1ffbf3dd92174cfbb4334dddd3b90403837ce5c9a2202e44%未知1
103GPT-5.1 (Medium) 2026-10-28config_e3713106475f831cac9815880c1f4a75e52ed91aeca6556bb571f86ce862106944%未知1
104Claude Sonnet 4.5 (High, 32K, 20250929) 2026-10-28config_a2dac6a8d32a637d2c81784dcb183ef0e973ffdab79c0fb7ed86d3d108f3305444%未知1
105Claude Opus 4.1 (20250805) 2026-10-28config_c69fd3c11d15628c48f50295afbb9cd60071a520baa68adc2a0084928cd9fb8943%未知1
106MiniMax-M2.5 2026-10-28config_cfe79ed60df7188779bc3aa3dd3f76eb54289cc686741ad9a223b69514cb7f1743%未知1
107Claude Sonnet 4.5 (20250929) 2026-10-28config_61277d2fed8999820bb9400b0b907b40d0d9e03320172fb81b99b1c7ac62313642%未知1
108Gemini 3 Flash (Minimal) 2026-10-28config_34eb618da9e9b607bec97d04c92bffe516b52b3f02473539ef8674b11756be8442%未知1
109MiniMax-M2.1 Preview 2026-10-28config_b2daacee10f3e9b05eaa6cb75989cbc85aef6edd0b19da1122c16da07720218b42%未知1
110Grok 4.20 Beta (Reasoning, 0309) 2026-10-28config_9f976ce8d423bebfee0ebd87588b09c860290f21ea354d5e0284cec79c4c2dd841%未知1
111Solar Pro 4 2026-10-28config_66097ba4157cafde82c9ccf0eef6c3dc4d75b2ee2f99fcb5de2e8de5f9a1b00140%未知1
112Gemma 4 31B 2026-10-28config_5b2957f29669afc60610e8cbb4fb74834cb83c5869da3e8cf96d0642771361b440%未知1
113DeepSeek-V3.2 (Thinking) 2026-10-28config_ddf188e0084b069810fcce60c958dc197b33a45fe06a3670c1b3dc1d2a2accfc39%未知1
114Qwen3.5-122B-A10B 2026-10-28config_ea7ef76be1f6686313c52a500b09204e3f69f62e4892c8a3495d541f22275b8f39%未知1
115Gemma 4 26B A4B 2026-10-28config_6226e52ab3ea11dd3377d5d38bde389e41966b2fa754849f6bd9070d78c1b27e39%未知1
116Qwen3.5-27B 2026-10-28config_76a655f5218dd7ac2e5692d4d6cdb4c1a3d02d369232cfb9ab6c333d0be4458f39%未知1
117Grok 4.3 2026-10-28config_9a1e9d7780c75d951f0ecd41e81cefb129e720a2961114e5fbaeee097f0ca58639%未知1
118Hy3 preview 2026-10-28config_3e1c945a4bbb988af58896242c8892e29e1bdb483d0d08c2e7fea5b531466d6c39%未知1
119Muse Glimmer 2026-10-28config_58a86e8119252e0a9427bd52072f1f447d037faaacb504253f3a0f7e7700e09138%未知1
120Laguna M.1 2026-10-28config_2e740cf9515fc1c0cd4b324010de5e74282c075343554e2ad1d35882fe0437ea38%未知1
121GPT-5.1 2026-10-28config_49c62ff88186b195ac4be26e746397ac8464c5d96db480049c60bc0d74af12ca37%未知1
122GLM-4.6 2026-10-28config_126ab9768458d1a1fa49c2e22bf76de79482ad132767435a892a6fed4767ede737%未知1
123GPT-5.2-Codex 2026-10-28config_342e066f8fc5f01e4701837b17d696224c505f07a524968b79f52f0a888feee136%未知1
124GPT-5.1-Codex 2026-10-28config_1f643cbfd962680e0ec85eeb8dca2df50088aa1b734ac457f04c65270f6b939036%未知1
125MiMo-V2-Flash (Non-Thinking) 2026-10-28config_83e3a3a9ba43054fe5c6c1472529c8b22daca25b3f806334ffbf6763b8c90efb35%未知1
126Claude Haiku 4.5 (20251001) 2026-10-28config_2fbd79994b26a3ba7bcdf37bb3986ccd5c79b7a14024aabcec8a5ba325d54fd835%未知1
127DeepSeek-V3.2 2026-10-28config_285ad99dd3ee2d9e091a6df003d665725539d5e6fd10bd654a33684630dbdcba34%未知1
128Kimi K2 Thinking Turbo 2026-10-28config_42da6c6f0d996ebb0c86c5229ca8182be06f10eea1042be71b6b2ea35f8bbc7634%未知1
129Laguna XS.2 2026-10-28config_8243a6058ccd615ef333619f6517fc6f41205512e367c1e5574265abcdddddaa31%未知1
130MiniMax-M2 2026-10-28config_7864c7a4ba76b4590a132a68daff5290b867e1529152f4ddee99e01bd593088931%未知1
131MiMo-V2-Flash (Thinking) 2026-10-28config_a6942492938c4aeb11ce4c1f62a9c65441d6c5d8dc48b6f03048e09039d948a430%未知1
132Qwen3-Coder-480B-A35B-Instruct 2026-10-28config_6656bebb33d290c8e00c51fd2ad0aa2f30a8b8055fe5d8211dc43eb3a6ddc76428%未知1
133DeepSeek-V3.2-Exp 2026-10-28config_1df482544c806c340dea2135f137eb2bdc6a9a3cffa797069971b51bee26fd4027%未知1
134Mistral Medium 3.5 2026-10-28config_9f28741307b78cb13f2178ca80cb4bc97fedb1acb42d6f448c8f36d4cf850d3e26%未知1
135Gemini 3.1 Flash-Lite Preview 2026-10-28config_8386f1124c7adc557e06bcaec7e64f9d1b1ac3fdd9188c7cf166d3ad4998d2e125%未知1
136KAT-Coder-Pro V1 2026-10-28config_8727c5978a47691405d201ba13355a6e766594c5901ea40b45a5186333ffc64b25%未知1
137Qwen3.5-35B-A3B 2026-10-28config_81f459a582189702a99b2fe0839297b41d53c3e78cb1602faeddb19d9701cd8325%未知1
138Qwen3.5-Flash 2026-10-28config_8f96f2e6a084820317432247719a5472fcea56242564433280fa09de07f927d223%未知1
139GPT-5.1-Codex-Mini 2026-10-28config_65db158611ae509a99169d9ba91008d41bc6bd08ce31840e2d91e36560c9393323%未知1
140Grok 4.1 Fast (Reasoning) 2026-10-28config_3fa24975048aa9b79314fff5274d6fbdf6b9f6a19c1db9615fb1a6e06e8c8e3d23%未知1
141Trinity Large Thinking 2026-10-28config_4b135e8eb19fba5544ba64242e9d40b2f1a39b0f8fc37e646e8fea8f6aac280723%未知1
142Mistral Large 3 2026-10-28config_e5a1e2a3b3a8294b2ccaf44318054f5fe08809eb8d374ed48cb10e16d8aeade622%未知1
143Gemini 2.5 Pro 2026-10-28config_1336732a0ef97f0f6d39514d45b693b0fbef53a147c359a21de9a252cf04ca8021%未知1
144Grok 4.1 (Thinking) 2026-10-28config_3375f4e37a7f1849bb62258a22b0019aa648ce72b8a22fced24881b960e7cfa719%未知1
145Devstral 2 2026-10-28config_454a6c5abe890a20c52c2ca7e653c351f37bb5ee4879742439031c4db7b9d02317%未知1
146Granite 4.1 8B 2026-10-28config_0f928d06bee8d8faa8f2874b62af99963f372c10ea698e25aff5e87e8a0db5d016%未知1
147Mercury 2 2026-10-28config_82131b142be530fb1b76bfeca018e8e6d916d716859c59dd76f9d30971f6195313%未知1
148Grok Code Fast 1 2026-10-28config_7741297a65e525edbd81ac9a6496d4c23fd74a0fd59a7fd90425e3d87884a69313%未知1
149Grok 4 Fast (Reasoning) 2026-10-28config_aece0d7cc9749b540b0eef59b46b4067a2efb71ec5d8e82ef8fae127e64abd8d12%未知1
150Devstral Medium (2507) 2026-10-28config_1e1f97bb9533e6f18a7498d415443eb242bdce527ecc97ab6ee8ae3e4171dcb70%未知1
对比该分组中的配置
独立依据不足,无法形成头部梯队
  • 校准尚未通过验证
  • 独立基准族的覆盖度低于要求的门槛
返回全部工作类别