Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Korean Elo

Chat & Writing · 2024-06-29

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 51505
Muse Spark1474
Claude Opus 51472
Muse Spark 1.11471
Gemini 3.5 Flash1467
Opus 4.71466
Gemini 3.1 Pro Preview1460
Opus 4.61456
Gemini 3 Pro Preview1450
GPT-5.51450
Opus 4.51448
Gemini 3 Flash Preview1448
Opus 4.81444
GPT-5.6 Sol1438
Sonnet 4.61437
Grok 4.11435
GLM-5.21433
MiMo-V2.5-Pro1433
GPT-5.41432
Sonnet 51428
ERNIE 5.11425
Kimi K2.61424
GLM-51423
GPT-5.3 Instant1422
DeepSeek-V4-Pro1421
Qwen3.7-Plus1419
MiMo-V2-Pro1415
GLM-5.11415
Gemini 2.5 Pro1415
Sonnet 4.51414
Inkling1412
Grok 4.51411
Kimi K2.51410
GLM-4.71407
GPT-5.6 Terra1407
Grok 4.31404
Gemini 3.1 Flash-Lite Preview1403
Opus 4.11401
GPT-51397
DeepSeek-V4-Flash1397
Loading Atlas data…