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-Flash1317Z.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 · Diagrams
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 · Diagrams | License | ||
|---|---|---|---|---|---|
| Score↓ | Rank | Votes | |||
| 1 | GLM-5.3-FlashZ.aiOpen |
1317±10 | 20 | 3,995 | MIT |
| 2 |  Kimi K2.6Moonshot AIOpen |
1298±10 | 35 | 4,304 | Modified MIT |
| 3 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeekOpen |
1297±19 | 37 | 1,085 | MIT |
| 4 |  Qwen3.8-27BAlibabaOpen |
1285±14 | 46 | 1,863 | Apache 2.0 |
| 5 |  Gemma 4 31BGoogleOpen |
1283±8 | 49 | 10,238 | Apache 2.0 |
| 6 | Kimi K2.5 (Thinking)Moonshot AIOpen |
1282±8 | 50 | 7,385 | Modified MIT |
| 7 |  MiMo-V2.6-ProXiaomiOpen |
1281±27 | 51 | 473 | MIT |
| 8 | Qwen3.5-397B-A17BAlibabaOpen |
1277±7 | 52 | 8,623 | Apache 2.0 |
| 9 | MiMo-V2.6-FlashXiaomiOpen |
1276±20 | 54 | 919 | MIT |
| 10 | MiMo-V2.5XiaomiOpen |
1269±8 | 59 | 7,723 | MIT |
| 11 |  MiniMax-M3MiniMaxOpen |
1266±9 | 62 | 5,289 | MiniMax Community License |
| 12 | Gemma 4 26B A4BGoogleOpen |
1264±9 | 66 | 6,239 | Apache 2.0 |
| 13 | Kimi K2.5 (Instant)Moonshot AIOpen |
1257±19 | 68 | 955 | Modified MIT |
| 14 | Qwen3-VL-235B-A22B-InstructAlibabaOpen |
1255±11 | 70 | 2,727 | Apache 2.0 |
| 15 |  Mistral Medium 3.5Mistral AIOpen |
1254±16 | 73 | 1,538 | Modified MIT |
| 16 | TInkling-SmallThinking MachinesOpen | 1251±14 | 75 | 2,071 | Apache 2.0 |
| 17 | Qwen3.5-122B-A10BAlibabaOpen |
1249±11 | 77 | 3,455 | Apache 2.0 |
| 18 | Qwen3.5-27BAlibabaOpen |
1249±8 | 78 | 7,927 | Apache 2.0 |
| 19 | Mistral Large 3Mistral AIOpen |
1240±13 | 85 | 2,334 | Apache 2.0 |
| 20 | NNVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)NVIDIAOpen | 1223±24 | 88 | 651 | OpenMDW-1.1 |
| 21 | Qwen3-VL-235B-A22B-ThinkingAlibabaOpen |
1214±27 | 91 | 464 | Apache 2.0 |
| 22 | GLM-4.6VZ.aiOpen |
1182±23 | 102 | 578 | MIT |
| 23 | Gemma 3 27B ITGoogleOpen |
1156±15 | 109 | 1,715 | Gemma |
| 24 | SStep-3StepFunOpen | 1155±30 | 110 | 347 | Apache 2.0 |
| 25 | GLM-4.5VZ.aiOpen |
1151±30 | 113 | 369 | MIT |
| 26 |  Llama 4 Maverick 17B 128E InstructMetaOpen |
1134±19 | 118 | 947 | Llama 4 |
| 27 | Mistral Small 3.2 (2506)Mistral AIOpen |
1125±18 | 119 | 1,166 | Apache 2.0 |
| 28 | Llama 4 Scout 17B 16E InstructMetaOpen |
1125±20 | 120 | 845 | Llama |
| 29 | Mistral Small 3.1 24B Instruct (2503)Mistral AIOpen |
1119±16 | 121 | 1,627 | Apache 2.0 |
| 30 |  Molmo 2 8BAi2Open |
1072±39 | 123 | 284 | Apache 2.0 |
Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0, vision config), Diagrams 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.