ChessBench (@chessbench) header
ChessBench (@chessbench) profile picture

ChessBench

@chessbench

A new benchmark tracking how well language models play chess. Watch the games, follow the reasoning move by move, track the leaderboard.

chessbench.ai
Joined June 2026
  • Tweets297
  • Following370
  • Followers145
63Media
Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)Photo by ChessBench (@chessbench)
Thanks @kaggle, @GoogleDeepMind, and @zapier for hosting such a great event this week!
Image from ChessBench (@chessbench)
9
220
Which of the following models will land with the highest overall score on ChessBench? Results will be published at 10:00am EST on 2026-11-03.
86%GPT-6.1 Terra
0%Grok 4.7
14%Muse Wonder 1.0
7 votes • Final results
5
2
114
It was GPT-6.1 Terra!
17
GPT-6.1 Terra, Grok 4.7, and Muse Wonder 1.0 have all been added to ChessBench!
1
1
72
chessbench.ai/leaderboard
Leaderboard on ChessBench

Leaderboard on ChessBench

Comprehensive leaderboard view of ChessBench model metrics.

chessbench.ai
1
15
@elonmusk @sama wanna vote?
21
@alexandr_wang @finkd any guesses?
22
chessbench.ai/leaderboard for results
49
I'm thrilled to be heading to @kaggle and @GoogleDeepMind's first Bench Summit this week. If you're going to be there, let me know -- I'd love to connect in person!
3
9
289
Elo ratings through 2026-10-22
4
168
A fun way to watch Elo ratings over time youtube.com/watch?v=eLm8kmEl…
Language Model Elo Ratings through 2026-10-22

Language Model Elo Ratings through 2026-10-22

All models benchmarked at chessbench.ai through 2026-10-22Music: ...

youtube.com
2
113
youtube.com/watch?v=eLm8kmEl…
Language Model Elo Ratings through 2026-10-22

Language Model Elo Ratings through 2026-10-22

All models benchmarked at chessbench.ai through 2026-10-22Music: ...

youtube.com
1
17
Are language models getting better at chess? You tell me.
Image from ChessBench (@chessbench)
3
6
122
Here's a fun look at it: youtube.com/watch?v=eLm8kmEl…
Language Model Elo Ratings through 2026-10-22

Language Model Elo Ratings through 2026-10-22

All models benchmarked at chessbench.ai through 2026-10-22Music: ...

youtube.com
11
Astra's dominance on the chessboard is striking.
Image from ChessBench (@chessbench)
1
82
chessbench.ai/
ChessBench // A Chess Benchmark for Language Models

ChessBench // A Chess Benchmark for Language Models

How well can AI play chess? ChessBench benchmarks language models at chess, ranking them by Elo rating. Updated daily.

chessbench.ai
36
ChessBench update: we now show each model at its best. Many models play under several settings, like different effort levels, temperatures, etc. We used to pool their stats. Now each model's Elo, accuracy and other numbers come from its best setting, picked by Overall Score. The tooltip names it.
1
3
114
chessbench.ai/
ChessBench // A Chess Benchmark for Language Models

ChessBench // A Chess Benchmark for Language Models

How well can AI play chess? ChessBench benchmarks language models at chess, ranking them by Elo rating. Updated daily.

chessbench.ai
31
Gemini 4 Argon has been added to ChessBench, coming in with a performance that is almost identical to gemini-3.8-flash.
Image from ChessBench (@chessbench)
2
6
385
chessbench.ai/skyline/overal…
Overall ranking on ChessBench

Overall ranking on ChessBench

The Overall ranking of AI language models on ChessBench, the AI chess benchmark.

chessbench.ai
2
59
chessbench.ai/timeline
33
Load more