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

GPT-6 Astra chess results⁠

Compare GPT-6 Astra'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 #5

2022 ChessBench Elo

Placement complete · 122 rated games

Wins / draws / losses
104 / 1 / 17
Result percentages
85% / 1% / 14%
Time per turn
14.4s
Cost per game
$1.452
Output tokens per game
9,068
Rejected %
0.02%

Medium #10

1767 ChessBench Elo

Placement complete · 118 rated games

Wins / draws / losses
74 / 13 / 31
Result percentages
63% / 11% / 26%
Time per turn
6.5s
Cost per game
$1.028
Output tokens per game
1,798
Rejected %
0.02%

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 3 of 12. 235 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.

  1. GPT-6.1 SOL (xHigh) vs GPT-6 Astra (Medium)1-0

    Checkmate · 71 half-moves · 2026-09-29 UTC

  2. GPT-6.1 SOL (xHigh) vs GPT-6 Astra (xHigh)0-1

    Checkmate · 130 half-moves · 2026-09-29 UTC

  3. GPT-6 Astra (Medium) vs GPT-6.1 SOL (xHigh)1-0

    Checkmate · 101 half-moves · 2026-09-29 UTC

  4. GPT-6 Astra (xHigh) vs GPT-6.1 SOL (xHigh)1-0

    Checkmate · 89 half-moves · 2026-09-29 UTC

  5. GPT-6 Astra (xHigh) vs GPT-6.1 SOL (Medium)1-0

    Checkmate · 93 half-moves · 2026-09-29 UTC

  6. GPT-6 Astra (Medium) vs GPT-6.1 SOL (Medium)1-0

    Checkmate · 91 half-moves · 2026-09-29 UTC

  7. GPT-6.1 SOL (Medium) vs GPT-6 Astra (xHigh)0-1

    Checkmate · 56 half-moves · 2026-09-29 UTC

  8. GPT-6.1 SOL (Medium) vs GPT-6 Astra (Medium)1-0

    Checkmate · 65 half-moves · 2026-09-29 UTC

  9. Claude Sonnet 5.5 (xHigh) vs GPT-6 Astra (Medium)1-0

    Checkmate · 57 half-moves · 2026-09-28 UTC

  10. Claude Sonnet 5.5 (xHigh) vs GPT-6 Astra (xHigh)1-0

    Checkmate · 59 half-moves · 2026-09-28 UTC

  11. GPT-6 Astra (Medium) vs Claude Sonnet 5.5 (xHigh)0-1

    Checkmate · 82 half-moves · 2026-09-28 UTC

  12. GPT-6 Astra (xHigh) vs Claude Sonnet 5.5 (xHigh)1-0

    Checkmate · 79 half-moves · 2026-09-28 UTC

  13. Claude Sonnet 5.5 (Medium) vs GPT-6 Astra (xHigh)0-1

    Checkmate · 68 half-moves · 2026-09-28 UTC

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

    Checkmate · 127 half-moves · 2026-09-28 UTC

  15. GPT-6 Astra (xHigh) vs Claude Sonnet 5.5 (Medium)1-0

    Checkmate · 79 half-moves · 2026-09-28 UTC

  16. GPT-6 Astra (Medium) vs Claude Sonnet 5.5 (Medium)1/2-1/2

    Draw at 150 total moves · 150 half-moves · 2026-09-28 UTC

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

    Checkmate · 118 half-moves · 2026-09-24 UTC

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

    Checkmate · 82 half-moves · 2026-09-24 UTC

  19. Space Bunny (Stealth) (Max) vs GPT-6 Astra (xHigh)0-1

    Checkmate · 52 half-moves · 2026-09-23 UTC

  20. GPT-6 Astra (Medium) vs Space Bunny (Stealth) (Max)1-0

    Checkmate · 43 half-moves · 2026-09-23 UTC

Cite these results

ChessBench. GPT-6 Astra chess results. https://chessbench.org/models/gpt-6-astra. 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.