# Can Claude play chess?

> Yes, Claude can play chess: it knows the rules and its newest models rarely make illegal moves. But it isn't an engine, and it still blunders.

- URL: https://thechesscoach.netlify.app/answers/can-claude-play-chess/
- Updated: 2026-10-22
- Author: Ignacio Soler

Yes, Claude can play chess. It knows the rules, the openings and the main ideas, and the newest Claude
models play a legal move almost every time. But Claude is a language model, not a chess engine. It
doesn't calculate long lines of moves the way Stockfish does, so it still blunders, and older or faster
Claude models can lose track of the board and try moves that aren't allowed.

Here is what public tests show, as of October 22, 2026. The numbers come from the
[AI Chess Leaderboard](https://dubesor.de/chess/chess-leaderboard) run by the developer Dubesor (data
updated October 21, 2026), which records every move its AI players make.

| What you ask of Claude | On its own | What the tests show |
|---|---|---|
| Explain rules, openings and plans | Yes, in plain words | Nothing checks its explanations against an engine |
| Play a legal move | Almost always, on the newest models | Claude Opus 5.5: 100% of move attempts legal when given the position and its legal moves, 98.2% when it only sees the moves played so far |
| Remember the board from the moves alone | Depends on the model | Claude Haiku 4.5: 98.6% legal when given the position, 51.6% from the move list alone |
| Avoid big mistakes | Not reliably | 2.8% of Claude Opus 5.5's moves were blunders, against 15% for Claude Haiku 4.5 |
| Calculate like an engine | No | It picks a likely-looking move; it doesn't search the replies |

On that leaderboard a blunder is a move that cuts the player's chances of winning by 15% or more.

## Can Claude play chess well?

Better than most people expect, and far below a real engine. On Dubesor's leaderboard, Claude Opus 5.5
has an Elo of 1571 ±97 after 35 games. In the same pool, maia5-1500, a neural network trained on more
than 10 million games by 1500-rated Lichess players, sits at 1554 ±90. A bot that plays random legal
moves sits at 419. On Maxim Saplin's [LLM Chess Leaderboard](https://maxim-saplin.github.io/llm_chess/),
which ties its scale to the Komodo Dragon engine's levels on Chess.com, Claude Opus 5.5 with high
reasoning scores 1575 ±113 (data of October 20, 2026).

Both authors warn that these numbers only mean something inside their own leaderboard. They are not
Chess.com or FIDE ratings. A fair reading: in these tests, the best Claude plays roughly as well as a
human-like 1500 bot, with wide error bars. We compare every leaderboard, and explain why they disagree,
in [What is Claude's chess Elo?](/answers/claude-chess-elo/)

Earlier Claude models were much weaker. On the same board, Claude 3.5 Sonnet is at 600 ±93 and Claude
Sonnet 4.5 at 659 ±72. So "Claude is bad at chess" was a fair complaint a year or two ago.

## Why Claude is sometimes bad at chess

A real game shows it. In August 2025, Kaggle and Google DeepMind ran an AI chess exhibition between
eight language models. Claude Opus 4 lost its quarterfinal 4–0 to Gemini 2.5 Pro, according to
[Chess.com's report](https://www.chess.com/news/view/kaggle-game-arena-chess-2025-day-1) of August 5, 2025.
In the first game Claude, playing Black, had a normal position after nine moves. Then it pushed a pawn in
front of its own castled king (g5).

> **Claude Opus 4 (Black) against Gemini 2.5 Pro, Kaggle Game Arena, August 2025**
> Position (FEN): `r1bq1rk1/pp2bpp1/2nppn1p/8/3NPP1B/2N5/PPPQ2PP/2KR1B1R b - - 1 10`
> Played: g5 — Pawn to g5 attacks the bishop, but loosens the pawns in front of Black's king
> Better: e5 — Pawn to e5 attacks the knight in the center and keeps the game about equal

Castling tucks the king in a corner behind a wall of pawns, and those pawns are its shelter. In our
check with Stockfish, the position before the pawn push is about equal (around +0.4 for White). After
it, White takes the pawn with a double attack, one move that threatens two things at once, and the
evaluation jumps to close to +3 for White. Chess.com's annotator notes that Claude's own reasoning saw
the weakness and judged it acceptable to get counterplay. It wasn't. Chess.com also noted that this
was the only quarterfinal with more games ending in checkmate than in forfeits for illegal moves.

Three things cause mistakes like this:

- **Claude predicts moves; it doesn't search them.** An engine checks the replies to a move, then the
  replies to those, many moves deep. A language model writes the move that seems most likely and gives
  reasons for it.
- **It has to keep the board in its head.** In a chat, the board is only text. That's why Claude Haiku
  4.5's legal moves drop from 98.6% to 51.6% when it sees only the move list. In the
  [Game Arena paper](https://arxiv.org/abs/2609.31473) by Google DeepMind and Kaggle (September 2026),
  models got four tries to play a legal move before losing the game, and Claude Haiku 4.5 often needed
  more than ten retries to finish one.
- **Confidence isn't accuracy.** This is true of every chatbot. In June 2025, ChatGPT lost to the 1979
  Atari 2600 Video Chess cartridge after mixing up its pieces, as
  [IBM Think reported](https://www.ibm.com/think/news/atari-wrecked-chatgpt-in-chess). Claude wasn't
  in that test; see [Can ChatGPT play chess?](/answers/can-chatgpt-play-chess/) and
  [why chatbots play illegal moves](/answers/why-does-chatgpt-play-illegal-moves-in-chess/).

## Can Claude Opus play chess better than Sonnet or Haiku?

Yes, on today's leaderboards. Dubesor's board, as of October 21, 2026:

- Claude Opus 5.5: 1571 ±97
- Claude Fable 5: 1465 ±88
- Claude Sonnet 5.5: 1321 ±108
- Claude Haiku 5.5: 1068 ±102

Letting the model think before it moves also matters a lot. On the open
[LLM Chess Benchmark](https://chessbenchllm.onrender.com/), Claude Opus 4.5 is rated 1012 with high
thinking and 175 with thinking off. If you want to try a game yourself, pick the strongest model you
have and turn on extended thinking.

## How to play a better game against Claude

- **Share the position every turn.** Paste the full move list or the position code (FEN) with each
  move. On Dubesor's leaderboard, Claude models given the position and its legal moves make far fewer
  illegal moves than when they only see the moves played.
- **Keep a real board open.** Play the moves on Lichess or Chess.com's analysis board so you can catch
  an illegal move right away.
- **Don't trust its evaluations.** When Claude says a position is winning, that's its opinion, not a
  calculation.

Our [guide to playing chess with Claude](/guides/play-chess-with-claude/) walks through the full setup.

## How Chess Coach helps

Chess Coach doesn't make Claude a stronger player, and it won't play against you. It does the job a
language model can't: checking the facts. It's a connector for Claude that reviews your finished
Chess.com and Lichess games with Stockfish on our own server. Claude then explains the key moments in
plain words on an interactive board, with a red arrow for the move you played and a green arrow for a
better one. It never helps with games in progress, and the free plan includes one in-depth review a day.
[Connect Chess Coach to Claude](/connect/), see [how the AI chess coach works](/features/ai-chess-coach/)
or read the [docs](/docs.html).

## FAQ

### Can Claude AI play chess?

Yes. Claude knows the rules and can play a full game in a chat. The newest models almost always play legal moves, but Claude doesn't calculate like a chess engine, so it still makes mistakes.

### Is Claude AI good at chess?

Better than older models, far from an engine. As of October 2026, Claude Opus 5.5 scores about 1570 on two public LLM chess leaderboards; on one of them that's close to a human-like 1500 bot. Those are not Chess.com or FIDE ratings.

### Can Claude Opus play chess?

Yes, and Opus is the strongest Claude at chess on current leaderboards. In August 2025 an earlier version, Claude Opus 4, lost 4–0 to Gemini 2.5 Pro in Kaggle's AI chess exhibition.

### Why is Claude bad at chess sometimes?

Claude is a language model: it writes a likely-looking move instead of searching ahead, and in a long game it can lose track of where the pieces are. Older and faster Claude models made many more illegal moves and blunders than the newest ones.

### Can you play chess against Claude?

Yes. Tell Claude you want to play, share the position or the full move list every turn, and keep a real board open to check its moves. Our guide shows the setup step by step.

## Related

- [Claude chess Elo: what the LLM leaderboards say (2026)](https://thechesscoach.netlify.app/answers/claude-chess-elo.md)
- [Can you play chess with Claude? How it works (2026)](https://thechesscoach.netlify.app/guides/play-chess-with-claude.md)
- [Can Claude analyze chess games? Yes, with Stockfish](https://thechesscoach.netlify.app/answers/can-claude-analyze-chess-games.md)
- [Chess MCP server for Claude and ChatGPT: Chess Coach](https://thechesscoach.netlify.app/connect.md)