LMArena Vision Arena
LMArena · vision-2026-08-27-51d09b2e834b · Blind human preferences for multimodal responses in LMArena's vision arena.
Model ranking
Publisher benchmark →Source | |||||||
|---|---|---|---|---|---|---|---|
| #1 | Claude Fable 5Anthropic | 1329.46 | — | 10,002 | claude-fable-5; 95% CI [1321.03632319, 1337.88661881]; votes 10002; rank 1unknown | Original sourcewinner eligible | Third-party benchmark |
| #2 | Kimi-K2.6Moonshot AI | 1280.71 | — | 15,378 | kimi-k2.6; 95% CI [1273.64165646, 1287.78511818]; votes 15378; rank 27unknown | Original sourcewinner eligible | Third-party benchmark |
| #3 | Qwen3.8-27BQwen | 1279.32 | — | 2,954 | qwen3.8-27b; 95% CI [1267.46655532, 1291.16933290]; votes 2954; rank 28unknown | Original sourcewinner eligible | Third-party benchmark |
| #4 | Claude Sonnet 5Anthropic | 1277.94 | — | 8,522 | claude-sonnet-5-high; 95% CI [1269.73992861, 1286.14906472]; votes 8522; rank 29unknown | Original sourcewinner eligible | Third-party benchmark |
| #5 | GPT-5.6 SolOpenAI | 1276.90 | — | 5,837 | gpt-5.6-sol-xhigh; 95% CI [1267.71657009, 1286.08047215]; votes 5837; rank 30unknown | Original sourcewinner eligible | Third-party benchmark |
| #6 | GPT-5.6 TerraOpenAI | 1268.99 | — | 5,774 | gpt-5.6-terra-xhigh; 95% CI [1259.82673197, 1278.15538857]; votes 5774; rank 33unknown | Original sourcewinner eligible | Third-party benchmark |
| #7 | Kimi-K2.5Moonshot AI | 1266.74 | — | 26,728 | kimi-k2.5-thinking; 95% CI [1260.83834046, 1272.64651923]; votes 26728; rank 36unknown | Original sourcewinner eligible | Third-party benchmark |
| #8 | Qwen3.5-397B-A17BQwen | 1264.80 | — | 25,997 | qwen3.5-397b-a17b; 95% CI [1258.85111028, 1270.75814841]; votes 25997; rank 38unknown | Original sourcewinner eligible | Third-party benchmark |
| #9 | MiniMax-M3MiniMax | 1255.42 | — | 13,390 | minimax-m3; 95% CI [1247.93588333, 1262.90862002]; votes 13390; rank 44unknown | Original sourcewinner eligible | Third-party benchmark |
| #10 | GPT-5.6 LunaOpenAI | 1254.30 | — | 5,857 | gpt-5.6-luna-xhigh; 95% CI [1245.05722338, 1263.53552757]; votes 5857; rank 45unknown | Original sourcewinner eligible | Third-party benchmark |
| #11 | Mistral-Medium-3.5-128BMistral AI | 1222.18 | — | 5,091 | mistral-medium-3.5; 95% CI [1212.39755732, 1231.95907443]; votes 5091; rank 67unknown | Original sourcewinner eligible | Third-party benchmark |
| #12 | Llama-4-Maverick-17B-128E-InstructMeta | 1141.47 | — | 6,936 | llama-4-maverick-17b-128e-instruct; 95% CI [1132.42029588, 1150.51619722]; votes 6936; rank 102unknown | Original sourcewinner eligible | Third-party benchmark |
| #13 | Llama-4-Scout-17B-16E-InstructMeta | 1118.08 | — | 6,467 | llama-4-scout-17b-16e-instruct; 95% CI [1108.62969338, 1127.52426769]; votes 6467; rank 110unknown | Original sourcewinner eligible | Third-party benchmark |
13 models ranked by the best winner-eligible current-version score when available, otherwise the best publisher-artifact score; highest first. Observed Aug 29, 2026.
Ranking protocol
arena rating · rating. Each model appears once; verified winner-eligible runs take precedence, and missing models are not imputed.
Acquisition coverage
13 published models from 148 source rows; 135 source identities remain quarantined.
Primary evidence