Atlas

Benchmarks

← All benchmarks

Arena Text — Longer Query (No Style Control)

Chat & Writing

Raw Arena rating for longer Text Arena queries without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.

Top models (higher is better)

ModelScore
Gemini 4 Argon1538
Claude Opus 5.51533
Claude Fable 5.11524
Claude Opus 51517
Opus 4.61517
Claude Fable 51510
Gemini 3.8 Flash1507
Opus 4.71505
MiMo-V2.6-Pro1500
Claude Sonnet 5.51495
Gemini 3.7 Flash1494
Kimi K31493
Muse Wonder1492
Muse Spark 1.31489
Qwen3.8-Max1489
GPT-5.51484
Opus 4.81484
GLM-5.31483
Gemini 3.5 Flash1482
Gemini 3.1 Pro Preview1482
GLM-5.3 Flash1482
Qwen3.7 Max Preview1482
MiMo-V2.5-Pro1481
GPT-5.6 Sol1481
GLM-5.21479
Opus 4.51479
Sonnet 4.61479
Sonnet 4.51475
Gemini 3.6 Flash1475
DeepSeek V4.1 Flash1474
GPT-5.41474
Muse Spark 1.21473
Gemini 3 Pro Preview1471
Kimi K2.61468
GLM-5.11467
Sonnet 51462
Grok 4.51462
GPT-6 Astra1462
ERNIE 5.11462
Muse Spark 1.11461
Loading Atlas data…