Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Entertainment, Sports, and Media Elo

Professional Work · 2025-11-05

Category-specific Elo score from the LMArena text-arena voting leaderboard. Higher Elo indicates stronger crowd-voted preference within this category.

Top models (higher is better)

ModelScore
Claude Fable 51496
Opus 4.61494
Opus 4.71481
GPT-5.6 Sol1470
Claude Opus 51468
Gemini 3 Pro Preview1468
Gemini 3.1 Pro Preview1464
Opus 4.81462
Muse Spark1461
Gemini 3.5 Flash1455
Gemini 3.6 Flash1454
Gemini 3 Flash Preview1453
Opus 4.51452
Muse Spark 1.11450
GPT-5.51448
Sonnet 4.61447
Kimi K31445
Grok 4.51445
GLM-5.11443
GPT-5.41443
Sonnet 4.51442
Qwen3.7 Max Preview1441
GLM-5.21440
MiMo-V2.5-Pro1439
GLM-51438
DeepSeek-V4-Pro1436
Grok 4.11435
Opus 4.11433
Gemini 3.5 Flash-Lite1432
Gemini 2.5 Pro1430
Sonnet 51430
GPT-5.6 Terra1430
ERNIE 5.11428
GPT-5.6 Luna1427
Kimi K2.61426
MiMo-V2-Pro1426
Qwen3.7-Plus1423
Kimi K2.51422
GPT-5.11420
Grok 4.31419
Loading Atlas data…