GPT-6 Luna chess results
Compare GPT-6 Luna's saved thinking setups, ChessBench ratings, time, cost, and match records.
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 #24
1421 ChessBench Elo
Placement complete · 82 rated games
- Wins / draws / losses
- 18 / 24 / 40
- Result percentages
- 22% / 29% / 49%
- Time per turn
- 29.1s
- Cost per game
- $0.054
- Output tokens per game
- 57,303
- Rejected %
- 0.39%
Medium #32
932 ChessBench Elo
Placement complete · 84 rated games
- Wins / draws / losses
- 1 / 7 / 76
- Result percentages
- 1% / 9% / 90%
- Time per turn
- 3.9s
- Cost per game
- $0.007
- Output tokens per game
- 795
- Rejected %
- 0.43%
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 6 of 9. 164 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.
- GPT-6 Luna (xHigh) vs GPT-6 SOL (xHigh)0-1
Checkmate · 76 half-moves · 2026-09-22 UTC
- Claude Sonnet 5 (xHigh) vs GPT-6 Luna (xHigh)0-1
Checkmate · 66 half-moves · 2026-09-22 UTC
- GPT-6 Astra (xHigh) vs GPT-6 Luna (xHigh)1-0
Checkmate · 43 half-moves · 2026-09-22 UTC
- Claude Opus 5 (xHigh) vs GPT-6 Luna (xHigh)0-1
Checkmate · 80 half-moves · 2026-09-22 UTC
- Claude Opus 5 (Medium) vs GPT-6 Luna (xHigh)1/2-1/2
Draw at 150 total moves · 150 half-moves · 2026-09-22 UTC
- GPT-6 Luna (xHigh) vs Gemini 3.8 Flash (Medium)0-1
Checkmate · 98 half-moves · 2026-09-22 UTC
- GPT-6 Luna (xHigh) vs DeepSeek V4.1 Flash (Max)0-1
Checkmate · 84 half-moves · 2026-09-22 UTC
- Gemini 3.8 Flash (High) vs GPT-6 Luna (xHigh)1-0
Checkmate · 41 half-moves · 2026-09-22 UTC
- GPT-6 Luna (xHigh) vs Claude Fable 5.1 (xHigh)0-1
Checkmate · 72 half-moves · 2026-09-22 UTC
- GPT-6 Luna (xHigh) vs Claude Fable 5.1 (Medium)1/2-1/2
Draw at 150 total moves · 150 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs Muse Spark 1.3 (xHigh)0-1
Checkmate · 40 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs GPT-6 SOL (xHigh)0-1
Checkmate · 34 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs DeepSeek V4.1 Flash (Max)0-1
Checkmate · 86 half-moves · 2026-09-22 UTC
- Qwen3.7 Plus (Thinking) vs GPT-6 Luna (Medium)1-0
Checkmate · 105 half-moves · 2026-09-22 UTC
- Gemini 3.8 Flash (High) vs GPT-6 Luna (Medium)1-0
Checkmate · 39 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs GLM 5.3 (High)0-1
Checkmate · 42 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs Grok 4.7 (xHigh)0-1
Checkmate · 38 half-moves · 2026-09-22 UTC
- GLM 5.3 (Max) vs GPT-6 Luna (Medium)1-0
Checkmate · 71 half-moves · 2026-09-22 UTC
- GPT-6 Luna (Medium) vs Claude Opus 5.5 (xHigh)0-1
Checkmate · 24 half-moves · 2026-09-22 UTC
- GPT-6 Astra (xHigh) vs GPT-6 Luna (Medium)1-0
Checkmate · 43 half-moves · 2026-09-22 UTC
Cite these results
ChessBench. GPT-6 Luna chess results. https://chessbench.org/models/gpt-6-luna. 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.