Atlas

Benchmarks

← All benchmarks

LMArena Text Overall No Style Control Elo

Chat & Writing · 2024-08-26

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 Argon1526
Claude Opus 5.51516
Claude Fable 5.11513
Claude Opus 51508
Opus 4.61501
Muse Wonder1501
Gemini 3.8 Flash1498
Muse Spark 1.31491
MiMo-V2.6-Pro1491
Claude Fable 51491
Opus 4.71490
Gemini 3.7 Flash1490
Qwen3.8-Max1484
Muse Spark 1.21482
Gemini 3.5 Flash1482
Gemini 3.1 Pro Preview1480
Gemini 3.6 Flash1480
Gemini 3 Pro Preview1479
Muse Spark 1.11478
Qwen3.7 Max Preview1475
Kimi K31475
Muse Spark1474
GLM-5.31474
Claude Sonnet 5.51473
GLM-5.3 Flash1472
GPT-5.51472
GLM-5.21470
GPT-5.41469
ERNIE 5.11468
Gemini 3 Flash Preview1466
DeepSeek V4.1 Flash1464
MiMo-V2.5-Pro1464
GLM-5.11463
Opus 4.81461
Sonnet 4.61458
Gemini 2.5 Pro1458
GPT-5.6 Sol1457
Kimi K2.61455
Qwen3.7-Plus (source unspecified)1455
MiMo-V2.6-Flash1452
Loading Atlas data…