Atlas

Benchmarks

← All benchmarks

Arena Vision — English (Style Controlled)

Multimodal

Style-controlled Vision Arena rating for English multimodal prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.

Top models (higher is better)

ModelScore
Claude Fable 51315
Gemini 3.6 Flash1313
Opus 4.71303
Opus 4.61300
Muse Spark 1.11289
Muse Spark1289
Claude Opus 51289
GPT-5.51283
Opus 4.81283
Sonnet 4.61283
GPT-5.41279
Grok 4.51278
GPT-5.6 Sol1276
Gemini 3 Pro Preview1276
Gemini 3.5 Flash1276
Gemini 3.1 Pro Preview1273
Kimi K2.61266
Sonnet 51265
Gemini 3.5 Flash-Lite1263
GPT-5.6 Terra1261
Gemini 3 Flash Preview1259
Qwen3.7-Plus1254
Qwen3.5 397B A17B1254
Gemma 4 31B1254
GPT-5.6 Luna1253
Kimi K2.51250
GPT-5.11250
GPT-5.4 Mini1249
MiniMax M31247
MiMo-V2.51247
Grok 4.31247
Gemini 2.5 Pro1244
GPT-5.21240
GLM 5V Turbo1239
Gemma 4 26B A4B1236
Gemini 2.5 Flash Preview (09-2025)1230
Qwen3.5 122B A10B1227
MiMo-V2-Omni1225
Gemini 3.1 Flash-Lite Preview1224
O3 (2025-04-16)1218
Loading Atlas data…