Atlas

Benchmarks

← All benchmarks

Arena Text — Entertainment, Sports & Media (No Style Control)

Professional Work

Raw Arena rating for entertainment, sports, and media industry prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.

Top models (higher is better)

ModelScore
Gemini 4 Argon1517
Claude Opus 5.51515
Claude Fable 5.11498
Opus 4.61492
Claude Fable 51482
Claude Opus 51482
Muse Wonder1481
Gemini 3.8 Flash1480
Gemini 3.7 Flash1478
Opus 4.71474
Gemini 3.1 Pro Preview1465
MiMo-V2.6-Pro1465
Gemini 3 Pro Preview1465
Qwen3.8-Max1464
Claude Sonnet 5.51462
Gemini 3.5 Flash1459
Muse Spark 1.31458
Gemini 3.6 Flash1456
Kimi K31452
GPT-5.6 Sol1450
Muse Spark1449
GPT-5.51449
GLM-5.21449
Gemini 3 Flash Preview1449
Qwen3.7 Max Preview1448
GLM-5.31448
DeepSeek V4.1 Flash1445
Muse Spark 1.21443
GLM-5.3 Flash1442
GLM-5.11442
Gemini 2.5 Pro1441
Opus 4.81440
GPT-5.41438
MiMo-V2.5-Pro1437
Muse Spark 1.11437
ERNIE 5.11436
Opus 4.51434
Grok 4.51434
Sonnet 4.61431
DeepSeek-V4-Pro1431
Loading Atlas data…