Vision and multimodal
تُقارن النتائج داخل المجموعة المتطابقة فقط، فلا يُرتَّب نموذج جرى اختباره بطريقة ما مقابل نموذج جرى اختباره بطريقة أخرى.
Reason over images, audio, or video
تستخدم مجموعات الترتيب مقاييس منفصلة. قارن التكوينات داخل المجموعة الواحدة فقط؛ فـ EvalRank لا يجمع الأنظمة المختلفة في قائمة ترتيب واحدة أبدًا.
الإجماع عبر المعايير
أنت أمام ترتيب واحد للنماذج عبر المقاييس المعتمدة في هذا الموضوع، موزونًا بالطريقة نفسها التي تُوزَن بها القرارات. وكل درجة تمثل حصة النموذج من أفضل نتيجة.
| الترتيب | النموذج | الحصة من الأفضل | المقاييس المرجعية |
|---|---|---|---|
| 1 | qwen38max | 100.0% | 1 |
| 2 | Claude Opus 4.7 | 99.9% | 1 |
| 3 | musespark | 99.5% | 1 |
| 4 | Claude Opus 4.6 | 99.5% | 1 |
| 5 | gemini3pro | 99.2% | 1 |
| 6 | GPT-5.5 | 98.9% | 1 |
| 7 | Gemini 3.5 Flash | 98.6% | 1 |
| 8 | musespark11 | 98.5% | 1 |
| 9 | gemini31propreview | 98.4% | 1 |
| 10 | grok45 | 98.4% | 1 |
| 11 | Claude Opus 4.8 | 98.4% | 1 |
| 12 | GPT-5.4 | 98.4% | 1 |
| 13 | GPT-5.2 Chat | 98.3% | 1 |
| 14 | gpt55instant | 98.2% | 1 |
| 15 | claudesonnet46 | 98.1% | 1 |
| 16 | Gemini 3 Flash | 97.9% | 1 |
| 17 | glm53flash | 97.8% | 1 |
| 18 | gemini35flashlite | 97.5% | 1 |
| 19 | kimik26 | 97.3% | 1 |
| 20 | qwen37plus | 97.2% | 1 |
| 21 | gemma431b | 97.1% | 1 |
| 22 | dolaseed20pro | 96.7% | 1 |
| 23 | Grok 4.20 Beta | 96.6% | 1 |
| 24 | Kimi K2.5 | 96.3% | 1 |
| 25 | mistrallarge4 | 96.3% | 1 |
| 26 | Grok 4.20 Multi-Agent Beta | 96.2% | 1 |
| 27 | gemini25pro | 96.0% | 1 |
| 28 | step5preview | 95.9% | 1 |
| 29 | qwen35397ba17b | 95.8% | 1 |
| 30 | mimov26pro | 95.7% | 1 |
| 31 | mimov26flash | 95.7% | 1 |
| 32 | qwen3827b | 95.6% | 1 |
| 33 | grok43 | 95.6% | 1 |
| 34 | gemma426ba4b | 95.5% | 1 |
| 35 | GPT-5.1 | 95.4% | 1 |
| 36 | ChatGPT-4o Latest | 95.3% | 1 |
| 37 | kimik25instant | 95.1% | 1 |
| 38 | gemini31flashlitepreview | 95.0% | 1 |
| 39 | mimov25 | 94.9% | 1 |
| 40 | minimaxm3 | 94.9% | 1 |
| 41 | glm5vturbo | 94.6% | 1 |
| 42 | gemini25flashpreview092025 | 94.6% | 1 |
| 43 | GPT-5.2 | 94.5% | 1 |
| 44 | qwen35122ba10b | 94.3% | 1 |
| 45 | gpt5chat | 94.3% | 1 |
| 46 | GPT-4.5 Preview | 94.2% | 1 |
| 47 | ERNIE-5.0-Preview | 93.8% | 1 |
| 48 | qwen3527b | 93.6% | 1 |
| 49 | mimov2omni | 93.5% | 1 |
| 50 | o3 | 93.5% | 1 |
| 51 | gemini25flash | 93.5% | 1 |
| 52 | qwen3vl235ba22binstruct | 93.5% | 1 |
| 53 | GPT-4.1 | 93.4% | 1 |
| 54 | inklingsmall | 93.0% | 1 |
| 55 | claudeopus4thinking16k | 92.9% | 1 |
| 56 | claudesonnet4thinking32k | 92.8% | 1 |
| 57 | nvidianemotron35supervl120ba12bnvfp4 | 92.6% | 1 |
| 58 | o4-mini | 92.4% | 1 |
| 59 | GPT-4.1 mini | 92.4% | 1 |
| 60 | mistralmedium35 | 92.3% | 1 |
| 61 | mistrallarge3 | 92.2% | 1 |
| 62 | Grok 4.1 Fast | 92.0% | 1 |
| 63 | claude37sonnetthinking32k | 91.7% | 1 |
| 64 | o1 | 91.7% | 1 |
| 65 | Claude Opus 4 | 91.5% | 1 |
| 66 | qwen3vl235ba22bthinking | 91.4% | 1 |
| 67 | Gemini 2.5 Flash-Lite Preview | 91.4% | 1 |
| 68 | Claude Sonnet 4 | 91.4% | 1 |
| 69 | Grok 4 | 91.1% | 1 |
| 70 | Claude 3.7 Sonnet | 90.4% | 1 |
| 71 | Gemini 2.0 Flash | 90.2% | 1 |
| 72 | glm46v | 89.3% | 1 |
| 73 | gemma327bit | 89.2% | 1 |
| 74 | Mistral Medium 3.1 | 89.2% | 1 |
| 75 | step1oturbo202506 | 88.9% | 1 |
| 76 | Mistral Medium 3 | 88.9% | 1 |
| 77 | hunyuanvision15thinking | 88.8% | 1 |
| 78 | glm45v | 88.7% | 1 |
| 79 | hunyuanlargevision | 88.4% | 1 |
| 80 | llama4maverick17b128einstruct | 88.1% | 1 |
| 81 | step3 | 88.1% | 1 |
| 82 | Mistral Small 3.2 | 87.7% | 1 |
| 83 | Gemini 2.0 Flash-Lite Preview | 87.4% | 1 |
| 84 | llama4scout17b16einstruct | 86.7% | 1 |
| 85 | Claude 3.5 Haiku | 86.7% | 1 |
| 86 | Mistral Small 3.1 24B Instruct | 86.7% | 1 |
| 87 | step1ovision32khighres | 86.5% | 1 |
| 88 | qwen25vl72binstruct | 86.2% | 1 |
| 89 | qwen25vl32binstruct | 86.1% | 1 |
| 90 | molmo28b | 85.5% | 1 |
| 91 | GPT-4 Turbo | 85.5% | 1 |
| 92 | GPT-4o mini | 84.4% | 1 |
| 93 | Pixtral Large | 84.3% | 1 |
| 94 | GPT-4.1 nano | 83.7% | 1 |
| 95 | qwen2vl72b | 83.4% | 1 |
| 96 | Gemini 1.5 Flash-8B | 82.4% | 1 |
| 97 | step1v32k | 81.9% | 1 |
| 98 | Claude 3 Opus | 81.7% | 1 |
| 99 | Molmo 72B | 80.4% | 1 |
| 100 | Hunyuan Standard Vision | 80.1% | 1 |
| 101 | llama3290bvisioninstruct | 79.4% | 1 |
| 102 | qwen2vl7binstruct | 79.3% | 1 |
| 103 | Pixtral 12B | 78.9% | 1 |
| 104 | internvl226b | 78.8% | 1 |
| 105 | amazonnovalite10 | 78.4% | 1 |
| 106 | amazonnovapro10 | 78.3% | 1 |
| 107 | Claude 3 Sonnet | 78.2% | 1 |
| 108 | yivision | 77.1% | 1 |
| 109 | ayavision32b | 77.0% | 1 |
| 110 | Claude 3 Haiku | 76.9% | 1 |
| 111 | Molmo 7B-D | 76.4% | 1 |
| 112 | llama3211bvisioninstruct | 76.4% | 1 |
| 113 | nvilainternal15bv1 | 75.8% | 1 |
| 114 | llavaonevisionqwen272bov | 75.2% | 1 |
| 115 | llava1634b | 74.2% | 1 |
| 116 | cogvlm2llama3chat19b | 74.1% | 1 |
| 117 | minicpmv26 | 74.0% | 1 |
| 118 | internvl24b | 73.7% | 1 |
| 119 | phi35visioninstruct | 70.7% | 1 |
| 120 | phi3vision128kinstruct | 67.7% | 1 |
نظام الساحة · مقارنة مزدوجة جماعية
استكشافي - لم يُصنَّف فائزًا بعدrg-vision-multimodal-arena-system-crowd-pairwise-arena-system-v1أدلة المستكشف
LMArena Vision
مصدر واحد. رُصدت في ؛ صالحة حتى .
| الترتيب | التكوين | القدرة | عدم اليقين | العائلات |
|---|---|---|---|---|
| 1 | Claude Fable 5 (High) 2026-10-19config_2fc50238a92d9751ea35074c52b2170d51985f2f6b9554d749ac80b8ef040f09 | 100% | غير معروف | 1 |
| 2 | Qwen3.8-Max 2026-10-19config_b105af9a815223ae9705a1d89539f8c84f54766ab728185de10094212176847d | 98% | غير معروف | 1 |
| 3 | Claude Opus 4.6 (High) 2026-10-19config_6d8411e4939d2152abe36e4b736f8be9faa4e72fd29f7fc9f084738dfac65533 | 98% | غير معروف | 1 |
| 4 | Claude Opus 4.7 2026-10-19config_9f33bff2e9728c30da5a8a7d26e1489700f226254261768deab8e62116112a65 | 98% | غير معروف | 1 |
| 5 | Claude Opus 4.7 (High) 2026-10-19config_48b171f2ffee9f19174ba19017c72151d566d6dbb734901e1b2759428cf59cc2 | 97% | غير معروف | 1 |
| 6 | Gemini 3.7 Flash (High) 2026-10-19config_3edb5fd33c7c59583d85a511f565d0818f0b079bc899b8ece6de7c67f5194ff6 | 97% | غير معروف | 1 |
| 7 | Muse Spark 2026-10-19config_fb01e2dc1a7d67463f16115a1bce067f147b8ec4f1d64258cfe7da8b45d70d51 | 97% | غير معروف | 1 |
| 8 | Claude Opus 4.6 2026-10-19config_bab0c8c449fcaf56513a6602ddbc4af423aed9954a087048e233dead1416d499 | 96% | غير معروف | 1 |
| 9 | GPT-6.1 Sol (Max) 2026-10-19config_7d85adf2b6a0d71e8b1fc8472a6433cc5eb1f82aefcd93cfa4e07aa69a72fa5b | 96% | غير معروف | 1 |
| 10 | Claude Opus 5.5 (High) 2026-10-19config_d2270b566111eda3ea91970277701681b96f942841bdda14eda26c09709ff138 | 96% | غير معروف | 1 |
| 11 | Muse Spark 1.2 (xHigh) 2026-10-19config_902333faeb7bfc67086b5df509c7e02a17feb726474f27a620f589975da54461 | 96% | غير معروف | 1 |
| 12 | Gemini 3.8 Flash (High) 2026-10-19config_b4dfa48e6a3a36778090a5d7a5bad975d490a4b9320434dc752070a1e62011fc | 96% | غير معروف | 1 |
| 13 | Muse Spark 1.3 (Max) 2026-10-19config_41ab01beb8f9ec4b5ee18cbf10a8273c08728c23e48b119a8fbb63519efda58d | 96% | غير معروف | 1 |
| 14 | Gemini 3 Pro 2026-10-19config_c61dd6afd86a0e9dfe10ce50c5e354073c2c08347c215198cd30bdf6836de33a | 95% | غير معروف | 1 |
| 15 | Claude Opus 5 (High) 2026-10-19config_21026b0ab42efd5568be8b3bfcf55556f1907384987dfa333ba50f2a3feb9db9 | 95% | غير معروف | 1 |
| 16 | Muse Spark 1.3 (xHigh) 2026-10-19config_665ce262c9d658d7a5a13186f9b3f975ed2b30b6d79639cfca0d4f1aedd2c4da | 95% | غير معروف | 1 |
| 17 | Claude Fable 5.1 (Max) 2026-10-19config_787a17c19fd1fdebe427718ce60522e2c9ce0a1493035b3bfd8e5462e10be69d | 95% | غير معروف | 1 |
| 18 | GPT-5.6 Sol (xHigh) 2026-10-19config_e88e8e1387d0bb4b04a6d1a86686a5e1fcc59a710e824d72708ae1780d34b3d7 | 95% | غير معروف | 1 |
| 19 | GPT-5.5 2026-10-19config_db86194517234f3675cbd45885960f81d2f7299de6b5a273ca30d8788458cf8d | 95% | غير معروف | 1 |
| 20 | Claude Opus 4.8 (High) 2026-10-19config_a4daf4a5a4a0906e5aaf77fee4800c38f21f550c091f264550f120af0e156527 | 95% | غير معروف | 1 |
| 21 | GPT-6 Astra (Max) 2026-10-19config_645dd67b7efce10b3447c350253bf037653146af18744060f363ef81396a0543 | 94% | غير معروف | 1 |
| 22 | GPT-5.4 (High) 2026-10-19config_971e46ec45be374bd6d262aad6b20be3454470cc560c34f5489b8f543b43cf89 | 94% | غير معروف | 1 |
| 23 | Gemini 3.5 Flash (Medium) 2026-10-19config_65136762e12683832c3065f7d8a13c361d6fd85737445522566960cc3ce5d247 | 94% | غير معروف | 1 |
| 24 | Gemini 3.5 Flash (High) 2026-10-19config_6a933328b835027963256e1b6c598a57c1bdaca381aa6bc8dbb1ced5d0f250d4 | 94% | غير معروف | 1 |
| 25 | GPT-5.5 (High) 2026-10-19config_81e9ed2bac02c59d85f0fc7bc3a17533cc7974fd9063eb6820831dbd500e3d90 | 94% | غير معروف | 1 |
| 26 | Gemini 3.6 Flash (High) 2026-10-19config_f02ed696019adc8cfb5b45fd657e2572e694066a6f9ea86a4fddc9a77565ca75 | 94% | غير معروف | 1 |
| 27 | Muse Spark 1.1 2026-10-19config_dc45fa8470327dcec96432c732ecc82934b3a669ebd5be742534f63e87ac22a6 | 93% | غير معروف | 1 |
| 28 | Gemini 3.1 Pro Preview 2026-10-19config_a8e2c48295ea11c5414b6451e18d6591b49f339a2bd0e5bf33f4dede66e89876 | 93% | غير معروف | 1 |
| 29 | Grok 4.5 2026-10-19config_bed5bf7b482e11ec61e30621c5426a70dbc59ea4e125ee40fa9c97547e197a02 | 93% | غير معروف | 1 |
| 30 | Claude Opus 4.8 2026-10-19config_81c00d79961d026114d90a28589fdb0cf8ba67a5cf60156c2bef3137e141ff3c | 93% | غير معروف | 1 |
| 31 | GPT-5.4 2026-10-19config_d2f49de5efaa295f786e1731d1c71d6cda6137d548d658d28d343478115ca330 | 93% | غير معروف | 1 |
| 32 | GPT-5.2 Chat (20260210) 2026-10-19config_2a9c259ca180eb5a2a713e0623add152921ebcf88fd14648d68e913cfec207d6 | 93% | غير معروف | 1 |
| 33 | GPT-5.5 Instant 2026-10-19config_518cdb922ba4dfce80b7c3d9b2574931e8994d814e3f163c2382f3bec18da83d | 92% | غير معروف | 1 |
| 34 | Claude Sonnet 4.6 2026-10-19config_21baa420b0c5e01da3d7d51cbd4c84586d0f90ff3747ee2b652619fc3d87bad2 | 92% | غير معروف | 1 |
| 35 | Gemini 3 Flash 2026-10-19config_95304c5e5f2986652c04ff9243fb34444e0b37e378572580893ca9737998044c | 92% | غير معروف | 1 |
| 36 | GLM-5.3-Flash 2026-10-19config_927a2f6f1f0daebce146fd217ac0fec29d2cd3064b421fc4fe161a932f35e2a9 | 91% | غير معروف | 1 |
| 37 | GPT-5.6 Terra (xHigh) 2026-10-19config_a9b30385589f6e5748d8d0977d8f4855bbab8befb3cf3ca5282d0348f094aa1e | 91% | غير معروف | 1 |
| 38 | Gemini 3.5 Flash-Lite 2026-10-19config_d102e21062bfb8938ded8259742b9bc00f1e209ee1c882739c723451d8e070ff | 90% | غير معروف | 1 |
| 39 | GPT-6 Sol (Max) 2026-10-19config_3b2c63f79cf0916c0c180cde0fc112cad5bc978b90ea5481bff4c1b3267b65fa | 90% | غير معروف | 1 |
| 40 | Claude Sonnet 5.5 (xHigh) 2026-10-19config_b1c8e0bc6fed9955c228bf0fc18e6e8460b3b22f25711dd5b3c96c76ae8bd330 | 90% | غير معروف | 1 |
| 41 | Kimi K2.6 2026-10-19config_55c279146e618783eb8fe91b6f28bc5d1623ab3327e4affeeae577cb1c1c9c09 | 90% | غير معروف | 1 |
| 42 | Qwen3.7-Plus 2026-10-19config_f0f0fb9039ef2a66ae7315d0316dadd17bb92a901ad3618ab7fcad25c57e4f07 | 89% | غير معروف | 1 |
| 43 | Grok 4.6 (High) 2026-10-19config_869165bb1837c4958c6ced5fab3d45f0f0674d281157c098216477fc7f5b2b09 | 89% | غير معروف | 1 |
| 44 | Claude Sonnet 5 (High) 2026-10-19config_7420059a038e5ce65d88a5dcfb8580a931738b46936f4018eb95ed671763bd7e | 89% | غير معروف | 1 |
| 45 | Gemma 4 31B 2026-10-19config_ac64e5545a93de1f466271e1f5a93c335ac4eb5318a3e3700f03ceadd14ec15b | 89% | غير معروف | 1 |
| 46 | DeepSeek-V4.1-Flash-20260910 (Max) 2026-10-19config_7631a77ef47c13fb9826a4f024119daff3dd37291217aaa77eb66b0b1da7d02e | 89% | غير معروف | 1 |
| 47 | Gemini 3 Flash (Minimal) 2026-10-19config_7b11f2ea36e1aae44e6f160fce16500df20de952d7a19b8d566da4dc893f7d38 | 89% | غير معروف | 1 |
| 48 | GPT-5.6 Luna (xHigh) 2026-10-19config_d2eb9213ccfb77a43836c854622c63c1666cfac22c465e571e1aab66204da1ec | 88% | غير معروف | 1 |
| 49 | Dola Seed 2.0 Pro 2026-10-19config_af7c915b37ee636d7d01ec1407080ab9857f7240dcd6dc13e61a9a31152c98c3 | 88% | غير معروف | 1 |
| 50 | Grok 4.20 Beta (Reasoning, 0309) 2026-10-19config_4cbd254b6497b4a914a42299384f37cf951af098dd41d8e9faf2f8e731098196 | 87% | غير معروف | 1 |
| 51 | Kimi K2.5 (Thinking) 2026-10-19config_456ccd430ee7d07a786f6e9074f251c36e47546caf4b11e989316a9ef942d4a7 | 87% | غير معروف | 1 |
| 52 | Mistral Large 4 2026-10-19config_cd198923343b49182379e92c73f2f3c448673c16d95cf7b9c043432c6ff294b8 | 87% | غير معروف | 1 |
| 53 | GPT-5.1 (High) 2026-10-19config_10e3c3c03a24cb0b81d662a5bebe9b5d43f8d255d3dd55ccaa7e9f5544b8bde4 | 87% | غير معروف | 1 |
| 54 | GPT-5.4 mini (High) 2026-10-19config_5423d05a894248acb259232a4cb87f524259ec54ca9c1031fe59ad5ac3c7d6b6 | 86% | غير معروف | 1 |
| 55 | Grok 4.20 Multi-Agent Beta (0309) 2026-10-19config_87ac146c6df6f797bfc5a8b13b0fd3322bbdadde54ee39213525c43cec19a123 | 86% | غير معروف | 1 |
| 56 | Grok 4.7 (xHigh) 2026-10-19config_d1a8813a7c53391ef224874f9c75440bf5022025b59a71d2a2ab90546ff9cda5 | 86% | غير معروف | 1 |
| 57 | Gemini 2.5 Pro 2026-10-19config_7e75d2d5fe38a54fc822cb223458b25c9132437123ea18c7eed03c1089ce7d9b | 86% | غير معروف | 1 |
| 58 | Step 5 Preview 2026-10-19config_035907a374463d3a92513ba12ad61a5184cbf1d41c9b613fb8bb1abba907085d | 86% | غير معروف | 1 |
| 59 | Qwen3.5-397B-A17B 2026-10-19config_1ee3035bb0555062b8e321f19c9adb59db117772e316453977d547c951c3bcbd | 85% | غير معروف | 1 |
| 60 | MiMo-V2.6-Pro 2026-10-19config_ab88f747fd7815e574b5a88fe60c94647f7fc68bbeb58405364cc1f2c0b71372 | 85% | غير معروف | 1 |
| 61 | MiMo-V2.6-Flash 2026-10-19config_6bb2ad59b064d0214a4d34d0675c466d40b58df21848334fd6fee16d66224c8a | 85% | غير معروف | 1 |
| 62 | GPT-5.2 (High) 2026-10-19config_fc4ca7ea2be1f4dd6fcf9e5f8dc50f41674a78371a1a3e81308dd75054b2e6c2 | 85% | غير معروف | 1 |
| 63 | Qwen3.8-27B 2026-10-19config_50485d9aaab49abd97ea8ff4ca0358d6604f96219557fc44570846271ecf45f1 | 85% | غير معروف | 1 |
| 64 | Grok 4.3 2026-10-19config_9c051d62c2f39ba3412fde0a2f4ebe98ceaac8d73b0c449105e422c072728caa | 84% | غير معروف | 1 |
| 65 | Gemma 4 26B A4B 2026-10-19config_6ed7fe999a443dee3b042adc547a8a8ac30a3c0d08ab387758176591fdbed7c1 | 84% | غير معروف | 1 |
| 66 | GPT-6 Luna (Max) 2026-10-19config_bf7516a58d6b6889c753e01bbccd8fd33b2e8a1ff4fd88bdea49d7a8706c6d60 | 84% | غير معروف | 1 |
| 67 | GPT-5.1 2026-10-19config_69bf9059e5f2be8010ee92d44b6a6edae5b6ac001c3215b10853b5973fd14dd6 | 84% | غير معروف | 1 |
| 68 | ChatGPT-4o Latest (20250326) 2026-10-19config_c14e6967a70a1afd1342d82bc7a5fb9167e81e706d4f45b68e6214b45657b2ec | 84% | غير معروف | 1 |
| 69 | Kimi K2.5 (Instant) 2026-10-19config_bac6aecf2441e1b551bbdca25b6914a4818c52de6ffe842b7b700e48b5b57d4a | 83% | غير معروف | 1 |
| 70 | Gemini 3.1 Flash-Lite Preview 2026-10-19config_585fd60a331a42040ad44fad1d86c113af57b58dc54b129086c0843e8d7c9f5b | 83% | غير معروف | 1 |
| 71 | MiMo-V2.5 2026-10-19config_2e83fc64578de0f5661dadce8071f29bd756ca726de56b5f3abcde1fc60f9e10 | 82% | غير معروف | 1 |
| 72 | MiniMax-M3 2026-10-19config_be143d629315e35425d6a882bb4e9889ab240dde10d1d9e1c419dcd532a181b3 | 82% | غير معروف | 1 |
| 73 | GLM-5V-Turbo 2026-10-19config_66c4812a93013c8473c1efb8b3386043e8d0e549c96f7cc2c5f115e92008f189 | 82% | غير معروف | 1 |
| 74 | Gemini 2.5 Flash Preview (09-2025) 2026-10-19config_8b69f56fe727c2eebb1b3bad2c56f28eb9c12854f22525c2a0bef9ccc4f3caff | 82% | غير معروف | 1 |
| 75 | GPT-5.2 2026-10-19config_3d8cb1b5ee5937f08eeada2b6a174a49cf1db17470ee76fbab64c3e1b711cc8e | 81% | غير معروف | 1 |
| 76 | Qwen3.5-122B-A10B 2026-10-19config_a02d808c61eac76bece0d07266cfbaa6776f1743295799a880aa3c50c24bfd31 | 81% | غير معروف | 1 |
| 77 | GPT-5 Chat 2026-10-19config_b73c099a7438eea274b1d4ce7d3a97e0f4c1c78694b27ffcba7a86378762812d | 81% | غير معروف | 1 |
| 78 | GPT-4.5 Preview (2025-02-27) 2026-10-19config_0d096f0eac7f0dcd9e6805bbd9f252162214be1ff0183a64658c7eb8e3ea008b | 80% | غير معروف | 1 |
| 79 | ERNIE-5.0-Preview (1220) 2026-10-19config_e2864698e8ccf4a01a7e59febf48f18afc3e3870b943d6310fc13c396f5a709c | 79% | غير معروف | 1 |
| 80 | Qwen3.5-27B 2026-10-19config_4ca61083c6b1ecafd0e1d690d0f65a1336abf75b63a732c241a593d45221a90c | 79% | غير معروف | 1 |
| 81 | MiMo-V2-Omni 2026-10-19config_68663a0b7f73eddaa6c71098205520404de4c2fdbac858ab061228436f0a888e | 78% | غير معروف | 1 |
| 82 | o3 (2025-04-16) 2026-10-19config_1cc9dcdaef569d3d2fb0fa95a4555fdfde88bbc9794701643189b29220f0cca8 | 78% | غير معروف | 1 |
| 83 | Gemini 2.5 Flash 2026-10-19config_10d3ea9d3a7c3d17b5b32864d016a4f17e443385931e23233db250d65587f12a | 78% | غير معروف | 1 |
| 84 | Qwen3-VL-235B-A22B-Instruct 2026-10-19config_ab8817c0360bdcdf834fe4f3a972615d4f65899595fe0f4124b1798a5762be8e | 78% | غير معروف | 1 |
| 85 | GPT-4.1 (2025-04-14) 2026-10-19config_7903b63773b091849150121223a7d4c947b16d2b435412e66239e8f970df1815 | 78% | غير معروف | 1 |
| 86 | GPT-5 (High) 2026-10-19config_da1b2bd3d6220a0396df561081f37d69f98b3647bedde0d14f62b884b3eff6ce | 77% | غير معروف | 1 |
| 87 | Inkling-Small 2026-10-19config_56eeed4b8a0e3a567009d3df584390ec38b42cc25e8c3c15881cdb6b62cc5b76 | 77% | غير معروف | 1 |
| 88 | Claude Opus 4 (Thinking 16K, 20250514) 2026-10-19config_53f5ff7d128471f7f45e587af4a6ab97764ac640b7afb47ee3d47e11fadd0611 | 76% | غير معروف | 1 |
| 89 | Claude Sonnet 4 (Thinking 32K, 20250514) 2026-10-19config_6f1a4d6457ab02db2c53c0bbef54cabd4739d57a1afc67e89f59055f35426266 | 76% | غير معروف | 1 |
| 90 | NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) 2026-10-19config_5102bc54e266322973b6f78cadd208fe0acaa736c76d78be57ffc783ba52a1c8 | 76% | غير معروف | 1 |
| 91 | o4-mini (2025-04-16) 2026-10-19config_948b08edab93f06d7471a91af0a5208357d26d29ac541ee1c5f5257a51d001db | 75% | غير معروف | 1 |
| 92 | GPT-4.1 mini (2025-04-14) 2026-10-19config_ba285eda0e8dadc7da283efe083508f2071d660fe4236b051b3e0676330b1829 | 75% | غير معروف | 1 |
| 93 | Mistral Medium 3.5 2026-10-19config_d3f8ab82e750172f67f1c3d77b072762322ee6b596eb0973500c8c44f14eee80 | 75% | غير معروف | 1 |
| 94 | Mistral Large 3 2026-10-19config_f9ad73d46fcc4c01373e6ab7256d5ba4086c0d37ab60bc94c24d04d04fb61273 | 74% | غير معروف | 1 |
| 95 | GPT-5.4 nano (High) 2026-10-19config_0bdd8c29c34ca97755ae0d4ddee16f7ff94e81e3bb19b707cb9007d18dd399e5 | 74% | غير معروف | 1 |
| 96 | Grok 4.1 Fast (Reasoning) 2026-10-19config_40c0aefa96afe67818fe5f6db46a1ea92a10be0ff2d9f783f15fb4c95156ab97 | 74% | غير معروف | 1 |
| 97 | Claude 3.7 Sonnet (Thinking 32K, 20250219) 2026-10-19config_d095f498f51067b5ddc63463172ed3a3174336375744bd663a572c742dc2b715 | 73% | غير معروف | 1 |
| 98 | o1 (2024-12-17) 2026-10-19config_5020c09f8f3a7b9e3cd223c7fffecadbdb9b610969e1b3cd9ee94b00e9676e3c | 73% | غير معروف | 1 |
| 99 | Claude Opus 4 (20250514) 2026-10-19config_19e4279b5231dbf64740ee4a68cb821462648a0938be44e88469911b33776832 | 72% | غير معروف | 1 |
| 100 | Qwen3-VL-235B-A22B-Thinking 2026-10-19config_a3a7ebe47c45870f84add22c1ea429de823a70c4f9dfeb1140d08b0142359e92 | 72% | غير معروف | 1 |
| 101 | Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) 2026-10-19config_1849471d43a96b42eee5d047d104550245861fe6105a2276115cd4e256df87a9 | 72% | غير معروف | 1 |
| 102 | Claude Sonnet 4 (20250514) 2026-10-19config_7037f17fb0c87089aef35e05613c5ec7117a6fd4685ed045471ac404104006a7 | 72% | غير معروف | 1 |
| 103 | Qwen-VL-Max (2025-08-13) 2026-10-19config_591db8f933a728876ec8efd5352391d174d479cd995ac8717e15122598ce30fb | 71% | غير معروف | 1 |
| 104 | GPT-5 mini (High) 2026-10-19config_0bf984f4ea3929cdd9542925f6c31520d3447df3477cf3e0c62f4b37c1a8a64a | 71% | غير معروف | 1 |
| 105 | Grok 4 (0709) 2026-10-19config_21ba5aa79d0c747b42129bde2eaf8dbb9b8c8100b57ea887ae817ee6b1aba66e | 71% | غير معروف | 1 |
| 106 | Gemini 1.5 Pro (002) 2026-10-19config_fa221cf716b5090aff6c640ac9f690c763f2f1f6cd76a7cdb92a07dd26fd2800 | 70% | غير معروف | 1 |
| 107 | Claude 3.7 Sonnet (20250219) 2026-10-19config_5ee21e1d63c1c9934d85f4b91bd3b030458afd9742b924fcc7174b68bd0dc6aa | 69% | غير معروف | 1 |
| 108 | Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025) 2026-10-19config_d8423f42ad3a301211dfe6d953b5b24cecac38dab0efbe5da2a656971a60c5ad | 69% | غير معروف | 1 |
| 109 | Gemini 2.0 Flash (001) 2026-10-19config_c524c9a346e46ff4e230f198addd65194351c1223d422067c89134a81fadac60 | 68% | غير معروف | 1 |
| 110 | GPT-4o (2024-05-13) 2026-10-19config_ff5a31ead743dd5a338fc2f134f000f4d7ad318a391aeecc20171a452ce85516 | 66% | غير معروف | 1 |
| 111 | GLM-4.6V 2026-10-19config_410cf05bc3a3be17f41ba20ec01f0d31e379a77054e2c936d985983ee0d0542d | 66% | غير معروف | 1 |
| 112 | Claude 3.5 Sonnet (20241022) 2026-10-19config_fe2a94627b4b39826708a5a4f70812c45754e4d5391d8a14eb8afe1997587d05 | 65% | غير معروف | 1 |
| 113 | Gemma 3 27B IT 2026-10-19config_24bf14df3559c005a9454d83073d8deb89f28673cd3a9873266d688f437be237 | 65% | غير معروف | 1 |
| 114 | Mistral Medium 3.1 (2508) 2026-10-19config_fd2eddb4cc95fa25b6700bda6aa6a825f6f1a92a15d105a0a9a07e8fe408e6ab | 65% | غير معروف | 1 |
| 115 | Step-1o Turbo (202506) 2026-10-19config_164772853d8e29028ab11102af314dd2509ffc8b8cc78013f203a49c3348a29c | 64% | غير معروف | 1 |
| 116 | Mistral Medium 3 (2505) 2026-10-19config_d959a5227b95a103ff44822a12938d6f09ec68e803e149993f75c7fa77f55727 | 64% | غير معروف | 1 |
| 117 | Hunyuan Vision 1.5 Thinking 2026-10-19config_57dc93aed8e256cba7173f57ce6c7c1a50d354105fa8767169c97e19209e0bb8 | 64% | غير معروف | 1 |
| 118 | GLM-4.5V 2026-10-19config_ea76023630ee83fcef731dcd527c445f8ce484e1d104dbc343a2c611e32015f9 | 64% | غير معروف | 1 |
| 119 | Hunyuan Large Vision 2026-10-19config_8585606707681fdb235b990f8d7fd192185ec5e6c9517c556b68cda297a01254 | 63% | غير معروف | 1 |
| 120 | GPT-5 nano (High) 2026-10-19config_306d82d4532c2f817e9145025136ce85d7b769b1f468d9c5a8ba74ef53facf09 | 62% | غير معروف | 1 |
| 121 | Llama 4 Maverick 17B 128E Instruct 2026-10-19config_7eac998082a22bd41afba4277396eb3e94977df68ade374adbcb3292e82dcbb2 | 62% | غير معروف | 1 |
| 122 | Claude 3.5 Sonnet (20240620) 2026-10-19config_f545d7e456d69f29f20648787be122805694c3b1b7746616b376fc5dbd9dae74 | 62% | غير معروف | 1 |
| 123 | Step-3 2026-10-19config_c53e896e93332ae6c85a738e91382ed375f868e357e980fe97169d8017a6637f | 62% | غير معروف | 1 |
| 124 | Gemini 1.5 Flash (002) 2026-10-19config_4a93b12bb13f5e4b06e47b259c815894c6baca314d73046c8d066d84408fdd16 | 61% | غير معروف | 1 |
| 125 | Mistral Small 3.2 (2506) 2026-10-19config_678fd00a66c940dbe7121251a533f7e3686c7bf77fe6bca9fa634cbc9de882d2 | 61% | غير معروف | 1 |
| 126 | Gemini 2.0 Flash-Lite Preview (02-05) 2026-10-19config_6350fce6cc2617800f99ad7e7e09576898ad47bd8f894f610772242a9c3b058e | 60% | غير معروف | 1 |
| 127 | Llama 4 Scout 17B 16E Instruct 2026-10-19config_3d8d9cc44fc57ea5b9369029917234e092d9e5409f441716e323d5404cdd5e3c | 58% | غير معروف | 1 |
| 128 | Claude 3.5 Haiku (20241022) 2026-10-19config_438e904df3fd2edfecc22253e5ad01312416ae7b8d3c7c43d9475e541794eee8 | 58% | غير معروف | 1 |
| 129 | Mistral Small 3.1 24B Instruct (2503) 2026-10-19config_53bc59d34727eb210dfcab711f25b88b270731604ce53074bd58124d6d398d1d | 58% | غير معروف | 1 |
| 130 | Step-1o Vision 32K (High Res) 2026-10-19config_1ef603aef13beac12159bbebae4d51aa0415d30c96d6472c314aed57dc2e3a3e | 57% | غير معروف | 1 |
| 131 | Qwen2.5-VL-72B-Instruct 2026-10-19config_14f59602bfe535fd6ab754c2d942d8bf2032b72702a8f2452b9d519912e1c1bb | 56% | غير معروف | 1 |
| 132 | Gemini 1.5 Pro (001) 2026-10-19config_a8b2c6e8d0ece3211a013701058c21e54f8380afb79c8695df7994ae8630e114 | 56% | غير معروف | 1 |
| 133 | Qwen2.5-VL-32B-Instruct 2026-10-19config_59433fb4ede9e0ae2f82b8af70a00e5277c6f61742cbcde8e2e877d25ebea1a2 | 56% | غير معروف | 1 |
| 134 | GPT-4o (2024-08-06) 2026-10-19config_bfc4018d875d438cd52d6751f5c62c6f7f5537db666320faea04e8e1b82928f7 | 55% | غير معروف | 1 |
| 135 | Molmo 2 8B 2026-10-19config_039b1ec85b314470d571dc99b587fb4f9387b083840dbb0fb3c9efb7f70b2956 | 54% | غير معروف | 1 |
| 136 | GPT-4 Turbo (2024-04-09) 2026-10-19config_3f1542bd66650abafb9cdd00f33610b53b054f788f7d4afa9f76c612e9cc83b8 | 54% | غير معروف | 1 |
| 137 | GPT-4o mini (2024-07-18) 2026-10-19config_8e134bef46d1a23539b3ab5270bf91173e835a16ecfca3102208204545468c59 | 51% | غير معروف | 1 |
| 138 | Pixtral Large (2411) 2026-10-19config_4b32e7072a935093f6384b4dd79bdaaa4bd0c95169158ee163385886fd842eb9 | 50% | غير معروف | 1 |
| 139 | GPT-4.1 nano (2025-04-14) 2026-10-19config_c410aea9e08a017c24ef1d21afbc31e195d23250d0a12cb9e5c0016390d11b3e | 49% | غير معروف | 1 |
| 140 | Qwen2-VL-72B 2026-10-19config_c3105032baab2dad5457c6c59866495dde4b3046a8e7eb91620e7f9295a15232 | 48% | غير معروف | 1 |
| 141 | Qwen-VL-Max (1119) 2026-10-19config_12f1584d06ea668241859d32b1002cabd14e6e6cf4b86b4b542b077d10964d93 | 48% | غير معروف | 1 |
| 142 | Gemini 1.5 Flash-8B (001) 2026-10-19config_aecacfb23e707bee1162c1da1804cdc3f56fff5a5ca537d5312549e8a4421844 | 45% | غير معروف | 1 |
| 143 | Step-1V 32K 2026-10-19config_5eb6a5da56db9c964604a4bd88a885002bcf9549f9cc2a6197692beada222990 | 43% | غير معروف | 1 |
| 144 | Claude 3 Opus (20240229) 2026-10-19config_7c5848f0617c09ba1f1321877530f6561cab3b1686ecbc245a331ce132667163 | 42% | غير معروف | 1 |
| 145 | Gemini 1.5 Flash (001) 2026-10-19config_1f7e4ff8a064eeb8423834ae32c2f0d34bc198882499e8867b05b7d17f1cca27 | 42% | غير معروف | 1 |
| 146 | Molmo 72B (0924) 2026-10-19config_0a649244127051cd020cae5b7912027502eee98aaca520c1ba7e56325dd52a69 | 38% | غير معروف | 1 |
| 147 | Hunyuan Standard Vision (2024-12-31) 2026-10-19config_35ce27f521ff36c22001c1937a8e58f5d4c6c3e51ab24cfd7833d47fb0d17404 | 38% | غير معروف | 1 |
| 148 | Llama 3.2 90B Vision Instruct 2026-10-19config_bd7069238a3f0278ee87c52476a4025c4903761bc34120e1a25a9723a17d14da | 35% | غير معروف | 1 |
| 149 | Qwen2-VL-7B-Instruct 2026-10-19config_3e7207188d0f0f32789b1bd30a16289a455fced3ee29e17e5e9769ff112e8c36 | 35% | غير معروف | 1 |
| 150 | Pixtral 12B (2409) 2026-10-19config_05cfc09a44411d7b1674da3348ef8e62f36593b81004d531a8fea25d5504823c | 34% | غير معروف | 1 |
| 151 | InternVL2 26B 2026-10-19config_03129bef035e1e8c1a315339d76de0383edf382a6c9fc2b5b332afb3f2e012a5 | 34% | غير معروف | 1 |
| 152 | Amazon Nova Lite 1.0 2026-10-19config_a462d4006bd9cdd1c740d8320564cffcc1ab7a465b911f10f47e8f5065e1db71 | 32% | غير معروف | 1 |
| 153 | Amazon Nova Pro 1.0 2026-10-19config_4ae586bfde51333130f6957900efde9b4917c55990dd4e386623eb826ee552e3 | 32% | غير معروف | 1 |
| 154 | Claude 3 Sonnet (20240229) 2026-10-19config_981f29746b86668ad3ba7bd09f9a29703379da0c59329d24dba421300235d657 | 32% | غير معروف | 1 |
| 155 | Yi Vision 2026-10-19config_d659a6aa2a14be08f69a824b94e4f32b3ba3035fe184b6d249370253ca7fe8e1 | 28% | غير معروف | 1 |
| 156 | Aya Vision 32B 2026-10-19config_85328779a80a8d27099872be9f72dc5bd672289f4c71383ba3794526f616a9ee | 28% | غير معروف | 1 |
| 157 | Claude 3 Haiku (20240307) 2026-10-19config_abd11ce67e5b71c6f0ec18a3f6e8907e3cdf13b63a94c46f86e707a48d6890c6 | 28% | غير معروف | 1 |
| 158 | Molmo 7B-D (0924) 2026-10-19config_b97d2d14c0f931d4014523ec211dff346e085bd39d8682ceee53ba2162229221 | 26% | غير معروف | 1 |
| 159 | Llama 3.2 11B Vision Instruct 2026-10-19config_941b0e5bbd9888959cfbd5b99917a71f11e7830646bd939f76160c596a7b2481 | 26% | غير معروف | 1 |
| 160 | nvila-internal-15b-v1 2026-10-19config_f05a336a38b52cb53bc64fb60530e0a748b34d784d45a5192e12c3a7e0a6d3d8 | 24% | غير معروف | 1 |
| 161 | LLaVA-OneVision Qwen2 72B OV 2026-10-19config_9819da4c1be8189b56bab9a71ca5470ef42563260e998f07562f5c5789d6eb10 | 23% | غير معروف | 1 |
| 162 | LLaVA 1.6 34B 2026-10-19config_ba018229fd45b2614eeba971b467a964ae7c1039567caab4e3d71678a1c89032 | 20% | غير معروف | 1 |
| 163 | CogVLM2 Llama3 Chat 19B 2026-10-19config_e4d2f1071637fb720bbe863579fc216d36147f17bcae458cbf5c04b2631817b8 | 19% | غير معروف | 1 |
| 164 | MiniCPM-V 2.6 2026-10-19config_b5b28f800df2a28f4e3205dbee3e762f87c5785d38eace9a628a34cc201c0ed9 | 19% | غير معروف | 1 |
| 165 | InternVL2 4B 2026-10-19config_6da16b8bf45cbb22633960b0ecfd2c617bf2e2101ed729515cd395182958c14b | 18% | غير معروف | 1 |
| 166 | Phi-3.5 Vision Instruct 2026-10-19config_3507694f567f91e165e1b6c836f60a40b2ba1652650d9d31d311bcfc27065b47 | 9% | غير معروف | 1 |
| 167 | Phi-3 Vision 128K Instruct 2026-10-19config_2156dca419dec8ad5117075173f3dbc8ebc4fed64fb3d9f0901f7241b5821113 | 0% | غير معروف | 1 |
لا توجد أدلة مستقلة كافية لتكوين مجموعة أعلى
- لم يتم التحقق من معايرة النتائج
- تغطية عائلات المعايير المستقلة أقل من الحد المطلوب