Atlas

Benchmarks

← All benchmarks

LMArena Text Arena English Elo

Chat & Writing · 2024-04-14

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 Argon1520
Claude Opus 5.51516
Muse Wonder1516
Opus 4.61513
Claude Fable 51511
Opus 4.71510
Muse Spark 1.31502
Claude Fable 5.11502
Gemini 3.8 Flash1498
Muse Spark1496
MiMo-V2.6-Pro1495
Kimi K31494
Claude Opus 51494
Muse Spark 1.21492
Claude Sonnet 5.51492
Qwen3.8-Max1491
GPT-6.1 Sol1491
GLM-5.31491
Opus 4.81490
Muse Spark 1.11490
Gemini 3.1 Pro Preview1490
GPT-5.6 Sol1489
DeepSeek V4.1 Flash1487
Gemini 3 Pro Preview1487
Gemini 3.6 Flash1487
GPT-6 Astra1487
Gemini 3.7 Flash1486
GPT-5.51485
GLM-5.21483
Sonnet 4.61483
GLM-5.11481
GLM-5.3 Flash1479
MiMo-V2.5-Pro1479
DeepSeek V4 Pro 08131479
Opus 4.51479
Gemini 3.5 Flash1478
ERNIE 5.11478
GPT-5.41476
Gemini 3 Flash Preview1476
Grok 4.51474
Loading Atlas data…