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.

Overall OCR Diagrams Homework Captioning Entity recognition Creative writing Humor English Chinese
#1 HumorData Oct 19, 2026
Muse SparkMeta · 1344

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 · Humor

22 models
All Open weights

Sorted 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 · Humor License
Score Rank Votes
1 Kimi K2.5 (Thinking)Moonshot AIOpen 1284±18 24 1,083 Modified MIT
2 Kimi K2.6Moonshot AIOpen 1280±25 28 590 Modified MIT
3 Gemma 4 31BGoogleOpen 1280±15 29 1,659 Apache 2.0
4 GLM-5.3-FlashZ.aiOpen 1279±23 30 671 MIT
5 Gemma 4 26B A4BGoogleOpen 1272±19 36 993 Apache 2.0
6 Qwen3.5-397B-A17BAlibabaOpen 1262±17 42 1,223 Apache 2.0
7 DeepSeek-V4.1-Flash-20260910 (Max)DeepSeekOpen 1260±45 47 166 MIT
8 Qwen3.5-122B-A10BAlibabaOpen 1243±27 52 468 Apache 2.0
9 Qwen3.8-27BAlibabaOpen 1235±32 56 347 Apache 2.0
10 MiniMax-M3MiniMaxOpen 1235±22 58 773 MiniMax Community License
11 Qwen3.5-27BAlibabaOpen 1227±18 60 1,195 Apache 2.0
12 Kimi K2.5 (Instant)Moonshot AIOpen 1226±46 62 155 Modified MIT
13 MiMo-V2.5XiaomiOpen 1226±18 63 1,147 MIT
14 Mistral Large 3Mistral AIOpen 1218±29 68 452 Apache 2.0
15 Mistral Medium 3.5Mistral AIOpen 1216±39 69 238 Modified MIT
16 Qwen3-VL-235B-A22B-InstructAlibabaOpen 1209±26 70 508 Apache 2.0
17 TInkling-SmallThinking MachinesOpen 1207±30 72 384 Apache 2.0
18 Gemma 3 27B ITGoogleOpen 1166±24 85 762 Gemma
19 Mistral Small 3.1 24B Instruct (2503)Mistral AIOpen 1142±23 89 933 Apache 2.0
20 Mistral Small 3.2 (2506)Mistral AIOpen 1140±30 90 481 Apache 2.0
21 Llama 4 Scout 17B 16E InstructMetaOpen 1102±45 92 191 Llama
22 Llama 4 Maverick 17B 128E InstructMetaOpen 1100±40 93 216 Llama 4

Scores: LMArena leaderboard-dataset (lmarena-ai on Hugging Face, CC-BY-4.0, vision config), Humor published Oct 19, 2026. Please credit the source when citing.

Sources & methodology

  1. Scores are Bradley-Terry Arena ratings fitted from human votes between two anonymous answers to the same image prompt.
  2. 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.
  3. Fields without public data (price, context length, release date…) are not shown; blanks are –. Nothing is estimated.
  4. 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.