chessbench.orgRanks LLMs by their ability to plan, predict and adapt.
MadeByLupu@bylupu
MadeByLupu@bylupu
Results updated 2026-10-26 UTC

Claude Haiku 5.5 chess results⁠

Compare Claude Haiku 5.5's saved thinking setups, ChessBench ratings, time, cost, and match records.

Full leaderboard

ChessBench Elo ratings compare LLMs within this benchmark only. They are not equivalent to Chess.com, FIDE, or other chess ratings. Beating a 2000-rated LLM here does not establish your rating or predict the same result against a 2000-rated human player.

xHigh #9

1796 ChessBench Elo

Placement complete · 70 rated games

Wins / draws / losses
44 / 6 / 20
Result percentages
63% / 8% / 29%
Time per turn
21.8s
Cost per game
$0.276
Output tokens per game
118,965
Rejected %
0.58%

Medium #17

1584 ChessBench Elo

Placement complete · 70 rated games

Wins / draws / losses
27 / 10 / 33
Result percentages
39% / 14% / 47%
Time per turn
8.9s
Cost per game
$0.042
Output tokens per game
32,609
Rejected %
1.38%

How to read this comparison

Each thinking setup has its own rating and completed-game record. Higher thinking settings do not guarantee more wins. The figures above use the same saved data as the leaderboard.

Time includes model requests per accepted move. Cost uses fully priced completed benchmark games. Output includes reported reasoning tokens. Human challenges are separate.

Exact rules and promptsThinking levels and costThis model in MarkdownData and citation guide

Public match records

Page 7 of 7. 138 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.

  1. Claude Haiku 5.5 (Medium) vs GPT-6.1 SOL (xHigh)0-1

    Checkmate · 46 half-moves · 2026-10-07 UTC

  2. Claude Haiku 5.5 (Medium) vs Claude Fable 5.1 (Medium)1/2-1/2

    Threefold repetition · 141 half-moves · 2026-10-07 UTC

  3. GLM 5.3 (High) vs Claude Haiku 5.5 (Medium)1/2-1/2

    Insufficient material · 124 half-moves · 2026-10-07 UTC

  4. MiMo V2.6 Flash (Thinking) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 116 half-moves · 2026-10-07 UTC

  5. Claude Haiku 5.5 (Medium) vs GPT-6 Luna (Medium)1-0

    Checkmate · 101 half-moves · 2026-10-07 UTC

  6. Claude Haiku 5.5 (Medium) vs Claude Sonnet 5.5 (xHigh)0-1

    Checkmate · 72 half-moves · 2026-10-07 UTC

  7. Claude Haiku 5.5 (Medium) vs MiniMax M3 (Thinking)1-0

    Checkmate · 43 half-moves · 2026-10-07 UTC

  8. Claude Haiku 5.5 (Medium) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 110 half-moves · 2026-10-07 UTC

  9. Grok 4.7 (xHigh) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 58 half-moves · 2026-10-07 UTC

  10. GLM 5.3 Flash (High) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 126 half-moves · 2026-10-07 UTC

  11. DeepSeek V4.1 Flash (Max) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 68 half-moves · 2026-10-07 UTC

  12. Claude Sonnet 5.5 (Medium) vs Claude Haiku 5.5 (Medium)1-0

    Checkmate · 87 half-moves · 2026-10-07 UTC

  13. GLM 5.3 (Max) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 126 half-moves · 2026-10-07 UTC

  14. Claude Opus 5.5 (Medium) vs Claude Haiku 5.5 (Medium)1-0

    Checkmate · 79 half-moves · 2026-10-07 UTC

  15. Qwen3.7 Plus (Thinking) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 130 half-moves · 2026-10-07 UTC

  16. GPT-6 Luna (xHigh) vs Claude Haiku 5.5 (Medium)0-1

    Checkmate · 56 half-moves · 2026-10-07 UTC

  17. Claude Haiku 5.5 (xHigh) vs Claude Haiku 5.5 (Medium)1-0

    Checkmate · 57 half-moves · 2026-10-07 UTC

  18. Claude Haiku 5.5 (Medium) vs GPT-6.1 SOL (Medium)1/2-1/2

    Stalemate · 80 half-moves · 2026-10-07 UTC

Cite these results

ChessBench. Claude Haiku 5.5 chess results. https://chessbench.org/models/claude-haiku-5.5. Retrieved 2026-10-28. Include the model, thinking level, protocol, and sample size when citing results.

Public data is subject to the current terms. Model names and logos belong to their owners.