Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Apr 26, 2026
5,967,203 votes
349 models
Rank Spread
28
1642
Moonshot · Modified MIT
1459±8
4,901$0.74 / $4.66256K
39
2749
Moonshot · Modified MIT
1449±4
24,838$0.60 / $3N/A
58
4777
Moonshot · Modified MIT
1432±7
8,206$0.44 / $2262.1K
61
5273
Moonshot · Modified MIT
1430±3
50,311$1.15 / $8262.1K
75
6191
Moonshot · Modified MIT
1418±6
11,805$0.60 / $2.50262.1K
79
6390
Moonshot · Modified MIT
1417±5
27,661$0.60 / $2.50131.1K

Default Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)