Atlas

Benchmarks

← All benchmarks

Arena Text — Non-English (Style Controlled)

Chat & Writing

Style-controlled Arena rating for the non-English Text Arena aggregate. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.

Top models (higher is better)

ModelScore
Gemini 4 Argon1508
Muse Wonder1498
Claude Opus 5.51497
Claude Fable 5.11496
Claude Fable 51493
Opus 4.71490
Opus 4.61489
Gemini 3.8 Flash1486
Gemini 3.7 Flash1486
Muse Spark 1.31484
Muse Spark 1.21484
Muse Spark 1.11483
Claude Opus 51481
Gemini 3.1 Pro Preview1479
Muse Spark1478
Gemini 3 Pro Preview1478
Kimi K31476
GPT-5.6 Sol1476
GPT-5.51474
Qwen3.8-Max1472
Gemini 3.6 Flash1472
Qwen3.7 Max Preview1470
Opus 4.81469
Gemini 3.5 Flash1469
GPT-5.41468
GPT-6.1 Sol1468
GLM-5.31465
GLM-5.3 Flash1465
Gemini 3 Flash Preview1464
GPT-6 Astra1463
GLM-5.21462
DeepSeek V4.1 Flash1460
MiMo-V2.6-Pro1460
Claude Sonnet 5.51458
Sonnet 4.61457
Opus 4.51457
GPT-5.6 Terra1456
Grok 4.51455
ERNIE 5.11453
Grok 4.11452
Loading Atlas data…