Atlas

Benchmarks

← All benchmarks

Arena Text — Polish (Style Controlled)

Chat & Writing

Style-controlled Arena rating for Polish-language Text Arena prompts. Higher ratings indicate stronger preference in blind pairwise user votes after adjusting for response style.

Top models (higher is better)

ModelScore
Gemini 3.5 Flash1527
Claude Fable 51512
Gemini 3 Pro Preview1504
Opus 4.61499
Opus 4.71498
Gemini 3 Flash Preview1497
Gemini 3.1 Pro Preview1497
Claude Opus 51497
Opus 4.81496
Muse Spark 1.11494
Grok 4.11489
Muse Spark1485
GPT-5.51482
GPT-5.41481
GPT-5.6 Sol1477
Sonnet 4.61473
MiMo-V2.5-Pro1472
GPT-5.3 Instant1471
Opus 4.51465
GPT-5.11465
DeepSeek-V4-Pro1463
ERNIE 5.11460
GPT-5.4 Mini1459
O3 (2025-04-16)1459
GPT-5.21458
Gemini 2.5 Pro1457
GLM-5.11457
Gemini 3.1 Flash-Lite Preview1454
Opus 4.11450
Grok 4.31450
Kimi K2.51447
GLM-51446
GPT-51445
MiMo-V2-Pro1444
Kimi K2.61444
MiniMax M31443
Qwen3.7-Plus1443
Qwen3.5 397B A17B1442
GLM-5.21439
Sonnet 4.51438
Loading Atlas data…