Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Hard Prompts English Elo

Chat & Writing · 2024-05-17

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
Opus 4.61538
Claude Fable 51533
Opus 4.71525
Claude Opus 51519
Opus 4.81513
Kimi K31508
Sonnet 4.61508
Gemini 3.1 Pro Preview1508
Muse Spark 1.11507
GPT-5.6 Sol1507
Muse Spark1507
Gemini 3.6 Flash1505
MiMo-V2.5-Pro1504
Gemini 3 Pro Preview1502
GLM-5.11502
GPT-5.51500
Opus 4.51498
Sonnet 51496
GPT-5.41496
Grok 4.51492
ERNIE 5.11492
Sonnet 4.51490
Gemini 3.5 Flash1490
Qwen3.7 Max Preview1490
GLM-5.21489
MiMo-V2-Pro1489
GPT-5.6 Luna1489
Gemini 3 Flash Preview1487
GLM-51487
Kimi K2.61487
GPT-5.6 Terra1484
DeepSeek-V4-Pro1484
Gemma 4 31B1483
Opus 4.11482
Qwen3.7-Plus1481
GPT-5.11479
Grok 4.11479
Hy31479
Kimi K2.51477
MiniMax M31477
Loading Atlas data…