Vision Model Leaderboard: Best Vision-Language Models
Ranked by LMArena Vision Arena scores: users upload an image, ask a question, and vote between two anonymous models’ answers.
- Top open-weight
GLM-5.3-Flash1299Z.ai
In LMArena Vision Arena data published Oct 19, 2026, Anthropic’s Claude Fable 5 (High) ranks #1 of 167 models with 1325 (14,714 votes).
Full leaderboard · OCR
30 modelsSorted by LMArena score by default; ± is half the 95% confidence interval. Category columns show the model’s score on that sub-board; – means no score.
| # | Model | LMArena · OCR | License | ||
|---|---|---|---|---|---|
| Score↓ | Rank | Votes | |||
| 1 | GLM-5.3-FlashZ.aiOpen |
1299±7 | 26 | 11,021 | MIT |
| 2 |  Kimi K2.6Moonshot AIOpen |
1291±7 | 33 | 11,758 | Modified MIT |
| 3 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeekOpen |
1282±12 | 41 | 2,786 | MIT |
| 4 |  Gemma 4 31BGoogleOpen |
1282±6 | 43 | 28,054 | Apache 2.0 |
| 5 |  Qwen3.8-27BAlibabaOpen |
1281±9 | 44 | 5,124 | Apache 2.0 |
| 6 | Kimi K2.5 (Thinking)Moonshot AIOpen |
1276±6 | 47 | 19,489 | Modified MIT |
| 7 | Qwen3.5-397B-A17BAlibabaOpen |
1271±5 | 51 | 22,696 | Apache 2.0 |
| 8 |  MiMo-V2.6-FlashXiaomiOpen |
1270±13 | 54 | 2,504 | MIT |
| 9 | MiMo-V2.6-ProXiaomiOpen |
1270±17 | 55 | 1,195 | MIT |
| 10 | Gemma 4 26B A4BGoogleOpen |
1268±7 | 56 | 16,862 | Apache 2.0 |
| 11 | Kimi K2.5 (Instant)Moonshot AIOpen |
1259±12 | 60 | 2,691 | Modified MIT |
| 12 |  MiniMax-M3MiniMaxOpen |
1259±6 | 61 | 13,947 | MiniMax Community License |
| 13 | MiMo-V2.5XiaomiOpen |
1256±6 | 64 | 20,901 | MIT |
| 14 | Qwen3-VL-235B-A22B-InstructAlibabaOpen |
1253±8 | 69 | 7,752 | Apache 2.0 |
| 15 | Qwen3.5-122B-A10BAlibabaOpen |
1251±7 | 70 | 9,185 | Apache 2.0 |
| 16 | Qwen3.5-27BAlibabaOpen |
1246±5 | 75 | 21,340 | Apache 2.0 |
| 17 | TInkling-SmallThinking MachinesOpen | 1243±9 | 76 | 5,655 | Apache 2.0 |
| 18 |  Mistral Medium 3.5Mistral AIOpen |
1233±10 | 84 | 3,905 | Modified MIT |
| 19 | Mistral Large 3Mistral AIOpen |
1228±8 | 85 | 6,194 | Apache 2.0 |
| 20 | NNVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)NVIDIAOpen | 1216±15 | 89 | 1,672 | OpenMDW-1.1 |
| 21 | Qwen3-VL-235B-A22B-ThinkingAlibabaOpen |
1212±16 | 91 | 1,322 | Apache 2.0 |
| 22 | GLM-4.6VZ.aiOpen |
1171±16 | 108 | 1,484 | MIT |
| 23 | SStep-3StepFunOpen | 1168±17 | 109 | 1,202 | Apache 2.0 |
| 24 | Gemma 3 27B ITGoogleOpen |
1156±10 | 112 | 6,196 | Gemma |
| 25 | GLM-4.5VZ.aiOpen |
1151±17 | 115 | 1,195 | MIT |
| 26 |  Llama 4 Maverick 17B 128E InstructMetaOpen |
1143±12 | 117 | 3,083 | Llama 4 |
| 27 | Mistral Small 3.2 (2506)Mistral AIOpen |
1134±11 | 119 | 4,083 | Apache 2.0 |
| 28 | Mistral Small 3.1 24B Instruct (2503)Mistral AIOpen |
1132±11 | 120 | 7,209 | Apache 2.0 |
| 29 | Llama 4 Scout 17B 16E InstructMetaOpen |
1117±12 | 121 | 2,788 | Llama |
| 30 |  Molmo 2 8BAi2Open |
1058±24 | 123 | 796 | Apache 2.0 |
Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0, vision config), OCR published Oct 19, 2026. Please credit the source when citing.
Sources & methodology
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
Vision config, published Oct 19, 2026; 167 models on the overall board.
- Scores are Bradley-Terry Arena ratings fitted from human votes between two anonymous answers to the same image prompt.
- Categories (OCR, diagrams, homework, captioning, Chinese/English…) are separate LMArena boards computed on prompts of that type, not a breakdown of the overall score; ranks can differ a lot.
- Fields without public data (price, context length, release date…) are not shown; blanks are –. Nothing is estimated.
- Synced daily. JSON API: /api/public/vision-leaderboard.php
This week
Collecting data: 1/7 days recorded; weekly changes appear after 7 days
Synced automatically once a day; ranks are compared only between real snapshots, never backfilled.FAQ
What is the best vision-language model right now?
In LMArena Vision Arena data published Oct 19, 2026, Anthropic’s Claude Fable 5 (High) ranks #1 of 167 models with 1325 (14,714 votes).
What is each vendor’s best vision model?
Top overall entry per vendor: Anthropic Claude Fable 5 (High) (1325, #1), Google Gemini 3.8 Flash (High) (1315, #7), Alibaba Qwen3.8-Max (1313, #10), Meta Muse Spark 1.3 (Max) (1308, #12), OpenAI GPT-5.4 (High) (1303, #18).
Which model is best at OCR?
On LMArena’s OCR board (123 models), Claude Fable 5 (High) is #1 with 1337.
What is the best open-weight vision model?
50 open-weight models are listed; the top one is GLM-5.3-Flash (1294, MIT).
How is this different from benchmarks like MMMU?
MMMU and similar benchmarks auto-score a fixed question set; this board comes from blind human votes on people’s own images and questions, reflecting real-use preference. They are not convertible.