Coding (frontend)
I risultati vengono confrontati solo all'interno dello stesso gruppo, così un modello testato in un modo non viene mai messo in classifica contro un modello testato in un altro.
Rank models and agents on building and iterating web interfaces from a specification
I gruppi di classifica usano scale diverse. Confronta le configurazioni solo all'interno dello stesso gruppo; EvalRank non appiattisce mai sistemi diversi in un'unica classifica.
Consenso tra i benchmark
Una classifica dei modelli sui benchmark ammessi per questo argomento, con lo stesso peso che si dà alle decisioni. Ogni punteggio è la quota del miglior risultato ottenuta dal modello.
| Posizione | Modello | Quota del migliore | Benchmark |
|---|---|---|---|
| 1 | mimov26flash | 100.0% | 1 |
| 2 | hy4preview | 99.6% | 1 |
| 3 | qwen38flashnext | 99.5% | 1 |
| 4 | mimov26pro | 99.3% | 1 |
| 5 | glm53flash | 98.1% | 1 |
| 6 | qwen3827b | 97.1% | 1 |
| 7 | minimaxm31flash | 96.7% | 1 |
| 8 | Claude Opus 4.7 | 95.0% | 1 |
| 9 | grok45 | 94.9% | 1 |
| 10 | mistrallarge4 | 94.3% | 1 |
| 11 | musespark11 | 94.2% | 1 |
| 12 | Claude Opus 4.6 | 93.9% | 1 |
| 13 | Claude Opus 4.8 | 93.8% | 1 |
| 14 | claudesonnet46 | 93.0% | 1 |
| 15 | seed21propreview | 92.8% | 1 |
| 16 | Qwen3.7-Max | 92.5% | 1 |
| 17 | kimik26 | 92.2% | 1 |
| 18 | glm51 | 92.1% | 1 |
| 19 | hy3 | 92.0% | 1 |
| 20 | Gemini 3.5 Flash | 91.0% | 1 |
| 21 | minimaxm3 | 90.6% | 1 |
| 22 | sparkx26 | 90.5% | 1 |
| 23 | qwen36maxpreview | 90.5% | 1 |
| 24 | mimov25pro | 90.4% | 1 |
| 25 | kimik27code | 90.0% | 1 |
| 26 | Claude Opus 4.5 | 89.7% | 1 |
| 27 | qwen36plus | 89.3% | 1 |
| 28 | gpt55codexharness | 88.9% | 1 |
| 29 | DeepSeek-V4-Pro | 88.4% | 1 |
| 30 | gemini31propreview | 88.4% | 1 |
| 31 | gpt54codexharness | 88.2% | 1 |
| 32 | Gemini 3 Flash | 88.0% | 1 |
| 33 | gemini3pro | 88.0% | 1 |
| 34 | mimov25 | 87.9% | 1 |
| 35 | Kimi K2.5 | 87.7% | 1 |
| 36 | beam10501ba23b | 87.7% | 1 |
| 37 | glm5 | 87.7% | 1 |
| 38 | glm47 | 87.7% | 1 |
| 39 | mimov2pro | 87.6% | 1 |
| 40 | gemini35flashlite | 87.6% | 1 |
| 41 | GPT-5 | 86.6% | 1 |
| 42 | gpt52 | 86.5% | 1 |
| 43 | inkling | 86.4% | 1 |
| 44 | inklingsmall | 86.1% | 1 |
| 45 | kimik25instant | 85.9% | 1 |
| 46 | GPT-5.4 | 85.6% | 1 |
| 47 | glm5vturbo | 85.6% | 1 |
| 48 | qwen35397ba17b | 85.5% | 1 |
| 49 | nvidianemotron35supervl120ba12bnvfp4 | 85.5% | 1 |
| 50 | minimaxm27 | 85.4% | 1 |
| 51 | GPT-5.1 | 85.2% | 1 |
| 52 | Claude Opus 4.1 | 84.9% | 1 |
| 53 | minimaxm25 | 84.7% | 1 |
| 54 | Claude Sonnet 4.5 | 84.6% | 1 |
| 55 | minimaxm21preview | 84.5% | 1 |
| 56 | Grok 4.20 Beta | 84.0% | 1 |
| 57 | solarpro4 | 83.7% | 1 |
| 58 | gemma431b | 83.6% | 1 |
| 59 | qwen35122ba10b | 83.1% | 1 |
| 60 | gemma426ba4b | 83.0% | 1 |
| 61 | qwen3527b | 83.0% | 1 |
| 62 | grok43 | 82.9% | 1 |
| 63 | hy3preview | 82.9% | 1 |
| 64 | museglimmer | 82.8% | 1 |
| 65 | lagunam1 | 82.4% | 1 |
| 66 | glm46 | 81.9% | 1 |
| 67 | gpt52codex | 81.8% | 1 |
| 68 | gpt51codex | 81.7% | 1 |
| 69 | Claude Haiku 4.5 | 81.3% | 1 |
| 70 | kimik2thinkingturbo | 80.7% | 1 |
| 71 | lagunaxs2 | 79.6% | 1 |
| 72 | minimaxm2 | 79.2% | 1 |
| 73 | MiMo-V2-Flash | 78.9% | 1 |
| 74 | qwen3coder480ba35binstruct | 77.9% | 1 |
| 75 | deepseekv32exp | 77.7% | 1 |
| 76 | mistralmedium35 | 77.2% | 1 |
| 77 | gemini31flashlitepreview | 76.7% | 1 |
| 78 | katcoderprov1 | 76.7% | 1 |
| 79 | qwen3535ba3b | 76.6% | 1 |
| 80 | qwen35flash | 76.0% | 1 |
| 81 | gpt51codexmini | 76.0% | 1 |
| 82 | Grok 4.1 Fast | 75.9% | 1 |
| 83 | trinitylargethinking | 75.6% | 1 |
| 84 | mistrallarge3 | 75.3% | 1 |
| 85 | gemini25pro | 74.9% | 1 |
| 86 | Grok 4.1 | 74.2% | 1 |
| 87 | devstral2 | 73.1% | 1 |
| 88 | granite418b | 72.8% | 1 |
| 89 | mercury2 | 71.5% | 1 |
| 90 | grokcodefast1 | 71.2% | 1 |
| 91 | Grok 4 Fast | 70.8% | 1 |
| 92 | Devstral Medium | 65.4% | 1 |
Sistema arena · Confronti a coppie del pubblico
Esplorativo - non è ancora un vincitore in classificarg-coding-frontend-arena-system-crowd-pairwise-arena-system-v1Evidenze dell'explorer
WebDev Arena
Fonte unica. Osservato il ; valido fino al .
| Posizione | Configurazione | Capacità | Incertezza | Famiglie |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) 2026-10-28config_084599a275e2ecc33b392f6b21b473b3099ce15e9f548adf538f09167cd57b67 | 100% | Sconosciuto | 1 |
| 2 | GPT-6 Astra (Max) 2026-10-28config_51830a6371ffd7ce2aaf4132cd8265e5dfa55cfebbd3512026ebe097defea979 | 95% | Sconosciuto | 1 |
| 3 | Claude Sonnet 5.5 (xHigh) 2026-10-28config_b566020b60b6f84a037865ec779e73f2745ee7f18eb149cb3fdd045e9ace80c5 | 95% | Sconosciuto | 1 |
| 4 | Gemini 4 Carbon (High) 2026-10-28config_b5885d0c4371c65bfa5847c537c31c7833df2e3a5f9c88dcbd86ca74a5e4dbba | 94% | Sconosciuto | 1 |
| 5 | GPT-6.1 Sol (Max) 2026-10-28config_ffacb76a2986667bcda568d04996bdf1e906a794075aa9a5f15db7a272cde569 | 92% | Sconosciuto | 1 |
| 6 | Claude Fable 5.1 (Max) 2026-10-28config_bd097b8d37cd0bd6889953b471a7374526f39306101b84ab14cf2a5a97142dd4 | 91% | Sconosciuto | 1 |
| 7 | Muse Wonder Full (Max) 2026-10-28config_d935215235a69c6a8870fd51180b96d36988a550f9073761f04c0327904f15b5 | 89% | Sconosciuto | 1 |
| 8 | Claude Sonnet 5.5 (High) 2026-10-28config_c50afdf1ac1726362497edd399c214c5b94210dc9f184fea660a6e85fe19de33 | 87% | Sconosciuto | 1 |
| 9 | Kimi K3.1 Pro (Max) 2026-10-28config_9a6cf0c4808e4dafde0c0f76ad266ad50c6c44590b1ba408e9f4ad2b718f4ebe | 84% | Sconosciuto | 1 |
| 10 | Claude Opus 5 (Max) 2026-10-28config_1e58c5f3745e8b97d9407c7d53132b338dad140fd249fd2d57561fc8034d3354 | 84% | Sconosciuto | 1 |
| 11 | Gemini 4 Argon (High) 2026-10-28config_6432998da74ca18daed355f209e566e8d01dcf3d0811d4582df594ba308e03be | 82% | Sconosciuto | 1 |
| 12 | GPT-6 Sol (Max) 2026-10-28config_bb31f3c169d756fa12582e0d16d19c9a1df889b0477bc261ba258b2053281d8b | 82% | Sconosciuto | 1 |
| 13 | Qwen3.8-Max (0902) 2026-10-28config_3764034f83f951a7a778d8061aa231c05b829ba8ea5c814b93e0d1dc98af03c1 | 82% | Sconosciuto | 1 |
| 14 | GPT-6.1 Terra (Max) 2026-10-28config_6e038f6481b3f31fecfabca695a00f623f0c36bf037d01ab933de16c4849c57e | 81% | Sconosciuto | 1 |
| 15 | Qwen3.8-Max 2026-10-28config_5d1f9f2850baa283cf067db9e43b5258529fc41cdd642d4eb0633c2f9f64d350 | 81% | Sconosciuto | 1 |
| 16 | DeepSeek-V4.1-Flash-20261017 (Max) 2026-10-28config_e606b306bd4d361da1bb0795f652b327407c6e332a634fbf942eaf2b5eace8ce | 80% | Sconosciuto | 1 |
| 17 | Claude Opus 5 (High) 2026-10-28config_b46e989a33026b7201ab0e25f73f1bab48bef0058b9baded39db0fe6613ba4bf | 79% | Sconosciuto | 1 |
| 18 | Kimi K3 (Max) 2026-10-28config_0b7ded79e4b765c6180aae8a37fd472c676d7686bc733999b6cb6bcffed276b5 | 79% | Sconosciuto | 1 |
| 19 | Muse Spark 1.3 (Max) 2026-10-28config_e472fb7e89171e0551becbbdcd5315969c25419ec8f47f83d56c3201f18cd825 | 79% | Sconosciuto | 1 |
| 20 | Muse Wonder (Max) 2026-10-28config_1b39a10afde9161478e6bedc63e6589d4cd3693e6a296e8d3734842652d0107e | 79% | Sconosciuto | 1 |
| 21 | Grok 4.7 (xHigh) 2026-10-28config_919a0fb21822b7fe4118472e6be38a3fd3e89cec9c523b133c507f21f76b4832 | 77% | Sconosciuto | 1 |
| 22 | MiMo-V2.6-Flash 2026-10-28config_efb00ed12debed0e7d64d768b27731e7c599e17ccc4a4d856b77883e43095e8b | 77% | Sconosciuto | 1 |
| 23 | Hy4 preview 2026-10-28config_7c3d10207795fff35f3d4a457a0c5e173d53b6195a0fa515789c02efedffa216 | 76% | Sconosciuto | 1 |
| 24 | Qwen3.8-Flash-Next 2026-10-28config_b218123a96fc95641c70960b3d516813bfdc9bdd7ee79acd4fafb6e1c2057a5f | 75% | Sconosciuto | 1 |
| 25 | MiMo-V2.6-Pro 2026-10-28config_a90bfe5f4a8e6813e428e8e39f946d8952a0aefc0955ed74014ebf0edaad4b31 | 75% | Sconosciuto | 1 |
| 26 | Claude Fable 5 (High) 2026-10-28config_2a73253495da68dd0fa25050a9742de1a851a2d17a8936e71a7af383a571ff55 | 75% | Sconosciuto | 1 |
| 27 | GLM-5.3 (Max) 2026-10-28config_6d1ef09daa9541e21f0e2d48ebf5c60516c0128797e2c7dbd46636b420e9b20a | 75% | Sconosciuto | 1 |
| 28 | Muse Spark 1.3 (xHigh) 2026-10-28config_46ceae567d6575fc78fdf1a8027aee115ccf3e0e7ee33bf5cbab5856500445c8 | 74% | Sconosciuto | 1 |
| 29 | DeepSeek-V4.1-Flash-20260910 (Max) 2026-10-28config_da6c8def458ed53d2e549a914f3d94d3a464df6033847bc54e9031cce7d6d04c | 74% | Sconosciuto | 1 |
| 30 | Grok 4.6 (High) 2026-10-28config_b1df94ccc507313b4046e201b43ed98dfa78ed94d4d8b2340610aba8b0759f34 | 74% | Sconosciuto | 1 |
| 31 | GPT-5.6 Sol (xHigh, Codex Harness) 2026-10-28config_3c9a490032ebda40472a4ad10859c7e0a71ea1d54b2da15e5a3e22f9e2cef7e1 | 74% | Sconosciuto | 1 |
| 32 | GLM-5.3-Flash 2026-10-28config_89ddbe2417e2a7b6eed655ea7c11869f5fb3cd7cfb9236eb4478a6510dfe1945 | 72% | Sconosciuto | 1 |
| 33 | GLM-5.2 (Max) 2026-10-28config_1c067e34d8425eca81e276822bddb10b98f8c46855f4d7865df23ba7e46c397d | 72% | Sconosciuto | 1 |
| 34 | Qwen3.8-27B 2026-10-28config_c1a6506519a672db95df472125ae2f25c30cb9a89e6618e8f618679bccf7d395 | 70% | Sconosciuto | 1 |
| 35 | Gemini 3.7 Flash (High) 2026-10-28config_9db5e2752ade2872af93694d3449028b62cdb7a5d15beac2d998b590e16a4c55 | 70% | Sconosciuto | 1 |
| 36 | Claude Haiku 5.5 (High) 2026-10-28config_303cacd37229916aca42b1fe17583bcd35fdc673056f2210bb70fe54eed26c37 | 70% | Sconosciuto | 1 |
| 37 | Gemini 3.8 Flash (High) 2026-10-28config_3652be9953d261d0050fb0995a1591ec590059df8fa5a73bbf30205c207bea2e | 69% | Sconosciuto | 1 |
| 38 | MiniMax-M3.1-Flash 2026-10-28config_aae5cd8ca2cceb3559c0e94a729b101533c7c41abac0b6bd8c1f42b81a0a3d42 | 69% | Sconosciuto | 1 |
| 39 | DeepSeek-V4-Pro (High, 20260813) 2026-10-28config_0b05f128d7a755dee259972d7da44d4fafd72bff6a44be7161b08b6e34860d6e | 69% | Sconosciuto | 1 |
| 40 | DeepSeek-V4-Flash (High) 2026-10-28config_8179bfb73cff50fbc85446cfeb2c853900a190b0d8cbfc1fe03f3d3c249569fb | 69% | Sconosciuto | 1 |
| 41 | GPT-6 Luna (Max) 2026-10-28config_0d0acb55cfa859062104ea03d70e02d556c74c0f61f5f1f84b2d9d5233574137 | 69% | Sconosciuto | 1 |
| 42 | Step 5 Preview (High) 2026-10-28config_5a7b7269210d74b8d558d4408cb9143ca73d6780513d8ba57aa8e373eab7082f | 68% | Sconosciuto | 1 |
| 43 | Claude Opus 4.7 (High) 2026-10-28config_a0893952f903309f38846f36b00231417668a2a4a891e2477648c3de6c45e70e | 66% | Sconosciuto | 1 |
| 44 | Claude Opus 4.8 (High) 2026-10-28config_7d7f2728fe3a8022b3b3376cd4756483d70fb0835c93ae2476ac9621f4b20e65 | 66% | Sconosciuto | 1 |
| 45 | Claude Opus 4.7 2026-10-28config_f6c7e371219a6d99e803f9396c66f2626b12ac473b7c243321fa2c843813cacc | 66% | Sconosciuto | 1 |
| 46 | Grok 4.5 2026-10-28config_a0ffd6609260d519939ed3c533540f5778ab3dbbfaec582e241e07c56021c3d5 | 65% | Sconosciuto | 1 |
| 47 | Claude Opus 4.6 (High) 2026-10-28config_71b3bad3c7d123207dc57d3ac4c4343e9ca0a2857ac27ac24576d820749c5627 | 64% | Sconosciuto | 1 |
| 48 | Mistral Large 4 2026-10-28config_2a06cd32756758c970720a67b63a99c63446d8c4acaef7e67fc87bbfee11e244 | 64% | Sconosciuto | 1 |
| 49 | Muse Spark 1.1 2026-10-28config_d4af76ee4a06e86c56cb3986c506879e5476a761a2bb84d729248567f5aec1a3 | 64% | Sconosciuto | 1 |
| 50 | Claude Sonnet 5 (High) 2026-10-28config_e6953c08753b928e5af7145fdd3ed3ee57c9b604244ec4547ff49c1b7be9bdc5 | 63% | Sconosciuto | 1 |
| 51 | Gemini 3.6 Flash (High) 2026-10-28config_54d01ce2e2f8cc1bac4e770892927598f97ff5f1540dae0135e15f88764eb427 | 63% | Sconosciuto | 1 |
| 52 | Claude Opus 4.6 2026-10-28config_56ead420187d3a8a7b41a1196ee296de6df5500d1b61df5d52980ca11803df51 | 63% | Sconosciuto | 1 |
| 53 | Claude Opus 4.8 2026-10-28config_4ba234aa493ae5cd6fea44ee1e421f71dd9703fcd0a57c609f05ea5fadfd41b5 | 63% | Sconosciuto | 1 |
| 54 | Muse Spark 1.2 (xHigh) 2026-10-28config_2885794b66bedac4effd325f8faa444f95f5ed7202e1361fa63ecc8e0910bc56 | 63% | Sconosciuto | 1 |
| 55 | Muse Spark Open (Max) 2026-10-28config_50a9393101152084234988b7b6d371bf8537ef6e8b1db0b23e69029ba4170933 | 62% | Sconosciuto | 1 |
| 56 | Claude Sonnet 4.6 2026-10-28config_548199089e3bce2ea1fad23b707f0fbd27632542663e46558b34f8de838d4a78 | 61% | Sconosciuto | 1 |
| 57 | GPT-5.6 Terra (xHigh, Codex Harness) 2026-10-28config_f3d6b5c8454dfbc0308eabfd4197f312930941106809e3a2207fcdc2640f655e | 61% | Sconosciuto | 1 |
| 58 | Seed2.1 Pro Preview 2026-10-28config_2061ddd4057137bcbba659bdd3ab7a76ae2ee7ec875667e4eb1a2460310d0403 | 61% | Sconosciuto | 1 |
| 59 | GPT-5.6 Luna (xHigh, Codex Harness) 2026-10-28config_78043f3b1bd3115773d2eb90686486e0644e7142a26e5161b55504a785ad2d08 | 61% | Sconosciuto | 1 |
| 60 | Qwen3.7-Max (20260517) 2026-10-28config_bcf6c53f0a79b9dcde7e010b3ca8707f18e63beeb94f3fd4cf4ab744f2b41ec9 | 60% | Sconosciuto | 1 |
| 61 | GPT-5.5 (xHigh, Codex Harness) 2026-10-28config_70a5b942d7e40d86b3f1cdb3108eef4050d50dadb54e82affa960f3ebb4c0114 | 60% | Sconosciuto | 1 |
| 62 | Kimi K2.6 2026-10-28config_c6b65847fc34a26ac47dbebc5e518ceef2497c3e172406918eecb24e3551ed17 | 59% | Sconosciuto | 1 |
| 63 | GLM-5.1 2026-10-28config_c3bd31b8773dec7bb6d5be4544335afa860ba332fd76a4de34f80ea032dede50 | 59% | Sconosciuto | 1 |
| 64 | Hy3 2026-10-28config_a25d9e603028ed8a31501b5c8e1a4490912dac5990811c0d88255da6e940bf90 | 59% | Sconosciuto | 1 |
| 65 | Gemini 3.5 Flash (High) 2026-10-28config_695672396293133a26af17b0ea320ea78772353ccfd9e56eb0f1596103a53a1b | 58% | Sconosciuto | 1 |
| 66 | Claude Opus 4.5 (High, 32K, 20251101) 2026-10-28config_c276df7ba009d3927718aa16804369178074fde0d4be596fdc3eb2a587483dff | 57% | Sconosciuto | 1 |
| 67 | Gemini 3.5 Flash (Medium) 2026-10-28config_d47df26fba1e9878228adbfb791d02dc1aa97e912e6af363c02cd22ccab91bfa | 57% | Sconosciuto | 1 |
| 68 | GPT-5.5 (High, Codex Harness) 2026-10-28config_ff25aae78aafa6a9921ab4e13dcb946a3cfab7992990491758191019640a7c5d | 56% | Sconosciuto | 1 |
| 69 | MiniMax-M3 2026-10-28config_262d41d8a151fa7ee8a19c2561ca43853c25dafa016de34d09ebca473b710063 | 56% | Sconosciuto | 1 |
| 70 | Spark-X2.6 2026-10-28config_a01f5f2a24041a4e571a38949c7c210752b6ce7deb372ccc6cf65d75f5a368b4 | 56% | Sconosciuto | 1 |
| 71 | Qwen3.6-Max-Preview 2026-10-28config_f2071e001e4c134cdc739b6a3be4a0d2b502b56f863c0b16fa99491ce742f5d1 | 56% | Sconosciuto | 1 |
| 72 | MiMo-V2.5-Pro 2026-10-28config_eeea2083450257442c0275fd4794aacec120a9b9461f9a1c973346de81123b2b | 55% | Sconosciuto | 1 |
| 73 | Kimi K2.7 Code 2026-10-28config_134e208a6e6322b3ca1021f7a929e7d5bed6e65ebb5b9b13e49467aae0949672 | 54% | Sconosciuto | 1 |
| 74 | Claude Opus 4.5 (20251101) 2026-10-28config_1c9c88a601597e26182aa01b7cbce9f1e45e65c6ec9cf631533fc42e7eed074b | 54% | Sconosciuto | 1 |
| 75 | DeepSeek-V4-Pro Preview (High) 2026-10-28config_8ead868ac1e453f93a57b1bb21e4d5e92b356054ed87d598c0a2595a13a3b02f | 53% | Sconosciuto | 1 |
| 76 | GPT-5.4 (High, Codex Harness) 2026-10-28config_a8222bb3ea402fb009e533e2a0318193ac20d53b231852ee5b478055bd7d6744 | 53% | Sconosciuto | 1 |
| 77 | Qwen3.6-Plus 2026-10-28config_70ed83ae1c9d9f52b318e624ce5ab5bc31290be301afbb3e795950d1c0515d6c | 53% | Sconosciuto | 1 |
| 78 | GPT-5.5 (Codex Harness) 2026-10-28config_5018e2bfd126e6a38eee61dce0c56dac184aec9f1b559bb8ecfa51f8b95cf6c5 | 52% | Sconosciuto | 1 |
| 79 | DeepSeek-V4-Pro 2026-10-28config_a3f4a1cea3817823a41ac0d901563112bdd255ba9525b8777bc5f0f6a6642b85 | 51% | Sconosciuto | 1 |
| 80 | Gemini 3.1 Pro Preview 2026-10-28config_98162614196039f883345c03893b46c09934bec5583988b76479f966de5996ee | 51% | Sconosciuto | 1 |
| 81 | GPT-5.4 (Medium, Codex Harness) 2026-10-28config_391927a789ad9cf0bb21aafb716eecb40c12448076b2ce63adee9dbec408fb29 | 50% | Sconosciuto | 1 |
| 82 | Gemini 3 Flash 2026-10-28config_cb3964cc363adff7228a3a48b2e468e142e2daeb0e858cf52219cb017de9ed07 | 50% | Sconosciuto | 1 |
| 83 | Gemini 3 Pro 2026-10-28config_b38e02e62231e15e625df727f57f79c574a41dbff08bdba8f157512c1da37283 | 50% | Sconosciuto | 1 |
| 84 | MiMo-V2.5 2026-10-28config_099667268b4ff0bb2b36c92b19f65fd6bfbe4cc198d286a2013bafdfe719c38c | 50% | Sconosciuto | 1 |
| 85 | Kimi K2.5 (Thinking) 2026-10-28config_20ff5d44e0e312dbd1d86d55c67a7b1df9fd631de82eb16ca67720cfe00c9737 | 49% | Sconosciuto | 1 |
| 86 | Beam 1.0 501B A23B 2026-10-28config_538d31ab0def325d05a738f7c8393ab691ff712c77884ce8a8dff5163bee4c60 | 49% | Sconosciuto | 1 |
| 87 | GLM-5 2026-10-28config_a728f37b4624d9eb170e19dc7e7afd20c0dfc1ad7017e680800c539029a5c8f7 | 49% | Sconosciuto | 1 |
| 88 | GLM-4.7 2026-10-28config_3cbac8f67d24c8fa2b4863c4102e8827c05e9504fe8135f65bca14989672d71b | 49% | Sconosciuto | 1 |
| 89 | MiMo-V2-Pro 2026-10-28config_d9d3bab83d4b223c0bde4a4003c9a05ed059c9ee2dd6c65361f6df2ab6e3e706 | 49% | Sconosciuto | 1 |
| 90 | Gemini 3.5 Flash-Lite 2026-10-28config_5f2c79ba2c116b5a7148f69d9544b6d99ba53d0bf0224146a423710a428c17a1 | 49% | Sconosciuto | 1 |
| 91 | DeepSeek-V4-Flash Preview (High) 2026-10-28config_3b11fb309f648d3f9ed4a3a59c0a0ea31ddd7359b8f1ba987bc60a67218fa04d | 49% | Sconosciuto | 1 |
| 92 | GPT-5 (Medium) 2026-10-28config_1b53fff12c8a6033457fbda61e70e78f256fdd4065953999217685a81e3970ea | 47% | Sconosciuto | 1 |
| 93 | GPT-5.2 2026-10-28config_b50462ec90c6a2b7c3c1f0ee5bb69e0475862b559acb14a9a02bf13f19950384 | 47% | Sconosciuto | 1 |
| 94 | Inkling 2026-10-28config_e6612e5cae60e38bdf5ca467aa101e87daa38ef6465ce456e2108876cbb97be6 | 47% | Sconosciuto | 1 |
| 95 | Inkling-Small 2026-10-28config_9c074775d10d8fdadbdccfdabe67708491e18d48e590fef83d8bf2d02a5a8818 | 46% | Sconosciuto | 1 |
| 96 | Kimi K2.5 (Instant) 2026-10-28config_a3735b8487d942fe5067c67c51408fbfcb925aa068795ce568da198eee8ef7f9 | 45% | Sconosciuto | 1 |
| 97 | GPT-5.4 2026-10-28config_f9d85f646c0a118c62dfd0862e19869e716cfe395f8cc7f138ae29c490c4d97b | 45% | Sconosciuto | 1 |
| 98 | GLM-5V-Turbo 2026-10-28config_c97363fe724129d4e908cd40c1bfc91efa6d86a3523465505bde8e89a2b2f7f3 | 45% | Sconosciuto | 1 |
| 99 | Qwen3.5-397B-A17B 2026-10-28config_76f6d4d75d27398a48f3b24ac013c8b991369ade3017b5719d0c522e5661cd4d | 45% | Sconosciuto | 1 |
| 100 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) 2026-10-28config_69357f72bc3cbdc8a058e0c1d037a720e0f96709f374dcfa8b1f0a633c7d8cfe | 44% | Sconosciuto | 1 |
| 101 | MiniMax-M2.7 2026-10-28config_44d547a42b68cf763ffab5f5846a1d7015e443c860904615f2fd846052f44fed | 44% | Sconosciuto | 1 |
| 102 | GPT-5.4 mini (High) 2026-10-28config_4daa1cbb84569c509b1ffbf3dd92174cfbb4334dddd3b90403837ce5c9a2202e | 44% | Sconosciuto | 1 |
| 103 | GPT-5.1 (Medium) 2026-10-28config_e3713106475f831cac9815880c1f4a75e52ed91aeca6556bb571f86ce8621069 | 44% | Sconosciuto | 1 |
| 104 | Claude Sonnet 4.5 (High, 32K, 20250929) 2026-10-28config_a2dac6a8d32a637d2c81784dcb183ef0e973ffdab79c0fb7ed86d3d108f33054 | 44% | Sconosciuto | 1 |
| 105 | Claude Opus 4.1 (20250805) 2026-10-28config_c69fd3c11d15628c48f50295afbb9cd60071a520baa68adc2a0084928cd9fb89 | 43% | Sconosciuto | 1 |
| 106 | MiniMax-M2.5 2026-10-28config_cfe79ed60df7188779bc3aa3dd3f76eb54289cc686741ad9a223b69514cb7f17 | 43% | Sconosciuto | 1 |
| 107 | Claude Sonnet 4.5 (20250929) 2026-10-28config_61277d2fed8999820bb9400b0b907b40d0d9e03320172fb81b99b1c7ac623136 | 42% | Sconosciuto | 1 |
| 108 | Gemini 3 Flash (Minimal) 2026-10-28config_34eb618da9e9b607bec97d04c92bffe516b52b3f02473539ef8674b11756be84 | 42% | Sconosciuto | 1 |
| 109 | MiniMax-M2.1 Preview 2026-10-28config_b2daacee10f3e9b05eaa6cb75989cbc85aef6edd0b19da1122c16da07720218b | 42% | Sconosciuto | 1 |
| 110 | Grok 4.20 Beta (Reasoning, 0309) 2026-10-28config_9f976ce8d423bebfee0ebd87588b09c860290f21ea354d5e0284cec79c4c2dd8 | 41% | Sconosciuto | 1 |
| 111 | Solar Pro 4 2026-10-28config_66097ba4157cafde82c9ccf0eef6c3dc4d75b2ee2f99fcb5de2e8de5f9a1b001 | 40% | Sconosciuto | 1 |
| 112 | Gemma 4 31B 2026-10-28config_5b2957f29669afc60610e8cbb4fb74834cb83c5869da3e8cf96d0642771361b4 | 40% | Sconosciuto | 1 |
| 113 | DeepSeek-V3.2 (Thinking) 2026-10-28config_ddf188e0084b069810fcce60c958dc197b33a45fe06a3670c1b3dc1d2a2accfc | 39% | Sconosciuto | 1 |
| 114 | Qwen3.5-122B-A10B 2026-10-28config_ea7ef76be1f6686313c52a500b09204e3f69f62e4892c8a3495d541f22275b8f | 39% | Sconosciuto | 1 |
| 115 | Gemma 4 26B A4B 2026-10-28config_6226e52ab3ea11dd3377d5d38bde389e41966b2fa754849f6bd9070d78c1b27e | 39% | Sconosciuto | 1 |
| 116 | Qwen3.5-27B 2026-10-28config_76a655f5218dd7ac2e5692d4d6cdb4c1a3d02d369232cfb9ab6c333d0be4458f | 39% | Sconosciuto | 1 |
| 117 | Grok 4.3 2026-10-28config_9a1e9d7780c75d951f0ecd41e81cefb129e720a2961114e5fbaeee097f0ca586 | 39% | Sconosciuto | 1 |
| 118 | Hy3 preview 2026-10-28config_3e1c945a4bbb988af58896242c8892e29e1bdb483d0d08c2e7fea5b531466d6c | 39% | Sconosciuto | 1 |
| 119 | Muse Glimmer 2026-10-28config_58a86e8119252e0a9427bd52072f1f447d037faaacb504253f3a0f7e7700e091 | 38% | Sconosciuto | 1 |
| 120 | Laguna M.1 2026-10-28config_2e740cf9515fc1c0cd4b324010de5e74282c075343554e2ad1d35882fe0437ea | 38% | Sconosciuto | 1 |
| 121 | GPT-5.1 2026-10-28config_49c62ff88186b195ac4be26e746397ac8464c5d96db480049c60bc0d74af12ca | 37% | Sconosciuto | 1 |
| 122 | GLM-4.6 2026-10-28config_126ab9768458d1a1fa49c2e22bf76de79482ad132767435a892a6fed4767ede7 | 37% | Sconosciuto | 1 |
| 123 | GPT-5.2-Codex 2026-10-28config_342e066f8fc5f01e4701837b17d696224c505f07a524968b79f52f0a888feee1 | 36% | Sconosciuto | 1 |
| 124 | GPT-5.1-Codex 2026-10-28config_1f643cbfd962680e0ec85eeb8dca2df50088aa1b734ac457f04c65270f6b9390 | 36% | Sconosciuto | 1 |
| 125 | MiMo-V2-Flash (Non-Thinking) 2026-10-28config_83e3a3a9ba43054fe5c6c1472529c8b22daca25b3f806334ffbf6763b8c90efb | 35% | Sconosciuto | 1 |
| 126 | Claude Haiku 4.5 (20251001) 2026-10-28config_2fbd79994b26a3ba7bcdf37bb3986ccd5c79b7a14024aabcec8a5ba325d54fd8 | 35% | Sconosciuto | 1 |
| 127 | DeepSeek-V3.2 2026-10-28config_285ad99dd3ee2d9e091a6df003d665725539d5e6fd10bd654a33684630dbdcba | 34% | Sconosciuto | 1 |
| 128 | Kimi K2 Thinking Turbo 2026-10-28config_42da6c6f0d996ebb0c86c5229ca8182be06f10eea1042be71b6b2ea35f8bbc76 | 34% | Sconosciuto | 1 |
| 129 | Laguna XS.2 2026-10-28config_8243a6058ccd615ef333619f6517fc6f41205512e367c1e5574265abcdddddaa | 31% | Sconosciuto | 1 |
| 130 | MiniMax-M2 2026-10-28config_7864c7a4ba76b4590a132a68daff5290b867e1529152f4ddee99e01bd5930889 | 31% | Sconosciuto | 1 |
| 131 | MiMo-V2-Flash (Thinking) 2026-10-28config_a6942492938c4aeb11ce4c1f62a9c65441d6c5d8dc48b6f03048e09039d948a4 | 30% | Sconosciuto | 1 |
| 132 | Qwen3-Coder-480B-A35B-Instruct 2026-10-28config_6656bebb33d290c8e00c51fd2ad0aa2f30a8b8055fe5d8211dc43eb3a6ddc764 | 28% | Sconosciuto | 1 |
| 133 | DeepSeek-V3.2-Exp 2026-10-28config_1df482544c806c340dea2135f137eb2bdc6a9a3cffa797069971b51bee26fd40 | 27% | Sconosciuto | 1 |
| 134 | Mistral Medium 3.5 2026-10-28config_9f28741307b78cb13f2178ca80cb4bc97fedb1acb42d6f448c8f36d4cf850d3e | 26% | Sconosciuto | 1 |
| 135 | Gemini 3.1 Flash-Lite Preview 2026-10-28config_8386f1124c7adc557e06bcaec7e64f9d1b1ac3fdd9188c7cf166d3ad4998d2e1 | 25% | Sconosciuto | 1 |
| 136 | KAT-Coder-Pro V1 2026-10-28config_8727c5978a47691405d201ba13355a6e766594c5901ea40b45a5186333ffc64b | 25% | Sconosciuto | 1 |
| 137 | Qwen3.5-35B-A3B 2026-10-28config_81f459a582189702a99b2fe0839297b41d53c3e78cb1602faeddb19d9701cd83 | 25% | Sconosciuto | 1 |
| 138 | Qwen3.5-Flash 2026-10-28config_8f96f2e6a084820317432247719a5472fcea56242564433280fa09de07f927d2 | 23% | Sconosciuto | 1 |
| 139 | GPT-5.1-Codex-Mini 2026-10-28config_65db158611ae509a99169d9ba91008d41bc6bd08ce31840e2d91e36560c93933 | 23% | Sconosciuto | 1 |
| 140 | Grok 4.1 Fast (Reasoning) 2026-10-28config_3fa24975048aa9b79314fff5274d6fbdf6b9f6a19c1db9615fb1a6e06e8c8e3d | 23% | Sconosciuto | 1 |
| 141 | Trinity Large Thinking 2026-10-28config_4b135e8eb19fba5544ba64242e9d40b2f1a39b0f8fc37e646e8fea8f6aac2807 | 23% | Sconosciuto | 1 |
| 142 | Mistral Large 3 2026-10-28config_e5a1e2a3b3a8294b2ccaf44318054f5fe08809eb8d374ed48cb10e16d8aeade6 | 22% | Sconosciuto | 1 |
| 143 | Gemini 2.5 Pro 2026-10-28config_1336732a0ef97f0f6d39514d45b693b0fbef53a147c359a21de9a252cf04ca80 | 21% | Sconosciuto | 1 |
| 144 | Grok 4.1 (Thinking) 2026-10-28config_3375f4e37a7f1849bb62258a22b0019aa648ce72b8a22fced24881b960e7cfa7 | 19% | Sconosciuto | 1 |
| 145 | Devstral 2 2026-10-28config_454a6c5abe890a20c52c2ca7e653c351f37bb5ee4879742439031c4db7b9d023 | 17% | Sconosciuto | 1 |
| 146 | Granite 4.1 8B 2026-10-28config_0f928d06bee8d8faa8f2874b62af99963f372c10ea698e25aff5e87e8a0db5d0 | 16% | Sconosciuto | 1 |
| 147 | Mercury 2 2026-10-28config_82131b142be530fb1b76bfeca018e8e6d916d716859c59dd76f9d30971f61953 | 13% | Sconosciuto | 1 |
| 148 | Grok Code Fast 1 2026-10-28config_7741297a65e525edbd81ac9a6496d4c23fd74a0fd59a7fd90425e3d87884a693 | 13% | Sconosciuto | 1 |
| 149 | Grok 4 Fast (Reasoning) 2026-10-28config_aece0d7cc9749b540b0eef59b46b4067a2efb71ec5d8e82ef8fae127e64abd8d | 12% | Sconosciuto | 1 |
| 150 | Devstral Medium (2507) 2026-10-28config_1e1f97bb9533e6f18a7498d415443eb242bdce527ecc97ab6ee8ae3e4171dcb7 | 0% | Sconosciuto | 1 |
Non ci sono abbastanza evidenze indipendenti per un gruppo di testa
- La calibrazione non è stata convalidata
- La copertura indipendente delle famiglie di benchmark è sotto la soglia richiesta