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
Gemini 4 Argon1509
Claude Opus 5.51502
Claude Fable 51492
Opus 4.61491
Muse Wonder1485
Opus 4.71480
Claude Fable 5.11479
Gemini 3.7 Flash1479
Gemini 3.8 Flash1477
GPT-5.6 Sol1471
Gemini 3 Pro Preview1469
Gemini 3.1 Pro Preview1469
Claude Sonnet 5.51464
Claude Opus 51463
Muse Spark1462
Gemini 3.6 Flash1461
Kimi K31461
Opus 4.81460
Muse Spark 1.31460
GPT-6.1 Sol1459
GPT-6 Astra1459
Qwen3.8-Max1459
Gemini 3.5 Flash1458
Opus 4.51454
Gemini 3 Flash Preview1454
Muse Spark 1.21450
DeepSeek V4.1 Flash1450
GLM-5.31449
GPT-5.51449
Muse Spark 1.11448
MiMo-V2.6-Pro1447
GLM-5.21446
Grok 4.51446
Sonnet 4.61445
Sonnet 4.51443
GPT-5.41441
Qwen3.7 Max Preview1441
Grok 4.61441
GLM-5.11441
GLM-5.3 Flash1439
Loading Atlas data…