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

Claude Opus 5.5 chess results⁠

Compare Claude Opus 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 #2

2102 ChessBench Elo

Placement complete · 90 rated games

Wins / draws / losses
80 / 4 / 6
Result percentages
89% / 4% / 7%
Time per turn
23.0s
Cost per game
$1.783
Output tokens per game
42,700
Rejected %
0.56%

Medium #6

1997 ChessBench Elo

Placement complete · 88 rated games

Wins / draws / losses
72 / 6 / 10
Result percentages
82% / 7% / 11%
Time per turn
14.0s
Cost per game
$0.670
Output tokens per game
10,203
Rejected %
0.55%

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 5 of 9. 176 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.

  1. GPT-5.6 Terra (xHigh) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 78 half-moves · 2026-09-22 UTC

  2. Claude Opus 5.5 (xHigh) vs GLM 5.3 Flash (High)1-0

    Checkmate · 45 half-moves · 2026-09-22 UTC

  3. Claude Opus 5.5 (xHigh) vs Claude Sonnet 5 (Medium)1-0

    Checkmate · 69 half-moves · 2026-09-22 UTC

  4. MiniMax M3 (Thinking) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 46 half-moves · 2026-09-22 UTC

  5. GLM 5.3 (High) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 36 half-moves · 2026-09-22 UTC

  6. Claude Sonnet 5 (xHigh) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 52 half-moves · 2026-09-22 UTC

  7. Claude Opus 5.5 (xHigh) vs Muse Spark 1.3 (Medium)1-0

    Checkmate · 65 half-moves · 2026-09-22 UTC

  8. DeepSeek V4.1 Flash (High) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 64 half-moves · 2026-09-22 UTC

  9. GPT-5.6 Terra (Medium) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 52 half-moves · 2026-09-22 UTC

  10. Claude Opus 5 (Medium) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 88 half-moves · 2026-09-22 UTC

  11. Claude Opus 5.5 (xHigh) vs Gemini 3.8 Flash (Medium)0-1

    Checkmate · 52 half-moves · 2026-09-22 UTC

  12. MiMo V2.6 Flash (Thinking) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 60 half-moves · 2026-09-22 UTC

  13. GLM 5.3 (Max) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 88 half-moves · 2026-09-22 UTC

  14. Claude Opus 5.5 (xHigh) vs GPT-6 Astra (Medium)1-0

    Checkmate · 45 half-moves · 2026-09-22 UTC

  15. Claude Opus 5.5 (xHigh) vs Gemini 3.8 Flash (High)1-0

    Checkmate · 129 half-moves · 2026-09-22 UTC

  16. GLM 5.3 Flash (Max) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 80 half-moves · 2026-09-22 UTC

  17. Muse Spark 1.3 (xHigh) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 62 half-moves · 2026-09-22 UTC

  18. Qwen3.7 Plus (Thinking) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 38 half-moves · 2026-09-22 UTC

  19. Claude Opus 5.5 (xHigh) vs Claude Opus 5 (xHigh)1-0

    Checkmate · 55 half-moves · 2026-09-22 UTC

  20. DeepSeek V4.1 Flash (Max) vs Claude Opus 5.5 (xHigh)0-1

    Checkmate · 86 half-moves · 2026-09-22 UTC

Cite these results

ChessBench. Claude Opus 5.5 chess results. https://chessbench.org/models/claude-opus-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.