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

Qwen3.7 Plus chess results⁠

Compare Qwen3.7 Plus'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.

Thinking #31

1075 ChessBench Elo

Placement complete · 113 rated games

Wins / draws / losses
4 / 38 / 71
Result percentages
4% / 33% / 63%
Time per turn
8.3s
Cost per game
$0.072
Output tokens per game
13,454
Rejected %
1.30%

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 6. 113 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.

  1. DeepSeek V4.1 Flash (Max) vs Qwen3.7 Plus (Thinking)1/2-1/2

    Insufficient material · 112 half-moves · 2026-09-15 UTC

  2. Qwen3.7 Plus (Thinking) vs Claude Sonnet 5 (Medium)1/2-1/2

    Insufficient material · 106 half-moves · 2026-09-15 UTC

  3. GLM 5.3 (High) vs Qwen3.7 Plus (Thinking)1-0

    Checkmate · 101 half-moves · 2026-09-15 UTC

  4. Gemini 3.8 Flash (High) vs Qwen3.7 Plus (Thinking)1-0

    Checkmate · 51 half-moves · 2026-09-15 UTC

  5. Claude Opus 5 (Medium) vs Qwen3.7 Plus (Thinking)1/2-1/2

    Insufficient material · 109 half-moves · 2026-09-15 UTC

  6. GPT-5.6 Luna (xHigh) vs Qwen3.7 Plus (Thinking)1/2-1/2

    Threefold repetition · 104 half-moves · 2026-09-15 UTC

  7. Qwen3.7 Plus (Thinking) vs GPT-5.6 Terra (xHigh)0-1

    Checkmate · 84 half-moves · 2026-09-15 UTC

  8. Qwen3.7 Plus (Thinking) vs GPT-6 Astra (Medium)0-1

    Checkmate · 42 half-moves · 2026-09-15 UTC

  9. Qwen3.7 Plus (Thinking) vs DeepSeek V4.1 Flash (High)0-1

    Checkmate · 42 half-moves · 2026-09-15 UTC

  10. Qwen3.7 Plus (Thinking) vs Claude Sonnet 5 (xHigh)1/2-1/2

    Insufficient material · 119 half-moves · 2026-09-15 UTC

  11. GPT-5.6 SOL (xHigh) vs Qwen3.7 Plus (Thinking)1-0

    Checkmate · 67 half-moves · 2026-09-15 UTC

  12. GPT-5.6 Luna (Medium) vs Qwen3.7 Plus (Thinking)1/2-1/2

    Threefold repetition · 123 half-moves · 2026-09-15 UTC

  13. Qwen3.7 Plus (Thinking) vs Claude Opus 5 (xHigh)1/2-1/2

    Stalemate · 98 half-moves · 2026-09-15 UTC

  14. GPT-6 Astra (xHigh) vs Qwen3.7 Plus (Thinking)1-0

    Checkmate · 57 half-moves · 2026-09-15 UTC

  15. GPT-5.6 SOL (Medium) vs Qwen3.7 Plus (Thinking)1/2-1/2

    Stalemate · 135 half-moves · 2026-09-15 UTC

  16. Qwen3.7 Plus (Thinking) vs GLM 5.3 Flash (High)0-1

    Checkmate · 66 half-moves · 2026-09-15 UTC

  17. Claude Fable 5.1 (Medium) vs Qwen3.7 Plus (Thinking)1-0

    Checkmate · 39 half-moves · 2026-09-15 UTC

  18. Qwen3.7 Plus (Thinking) vs MiniMax M3 (Thinking)1/2-1/2

    Insufficient material · 146 half-moves · 2026-09-15 UTC

  19. Qwen3.7 Plus (Thinking) vs Muse Spark 1.3 (Medium)0-1

    Checkmate · 52 half-moves · 2026-09-15 UTC

  20. Qwen3.7 Plus (Thinking) vs Muse Spark 1.3 (xHigh)0-1

    Checkmate · 50 half-moves · 2026-09-15 UTC

Cite these results

ChessBench. Qwen3.7 Plus chess results. https://chessbench.org/models/qwen3.7-plus. 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.