MiniMax M3 chess results
Compare MiniMax M3'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.
Thinking #29
1261 ChessBench Elo
Placement complete · 119 rated games
- Wins / draws / losses
- 15 / 33 / 71
- Result percentages
- 13% / 27% / 60%
- Time per turn
- 33.7s
- Cost per game
- $0.541
- Output tokens per game
- 165,895
- Rejected %
- 3.72%
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 4 of 6. 119 visible replays. Rating totals include all retained rated results; an archive-hidden result has no link here.
- MiniMax M3 (Thinking) vs GLM 5.3 Flash (High)0-1
Checkmate · 84 half-moves · 2026-09-17 UTC
- GPT-5.6 Luna (Medium) vs MiniMax M3 (Thinking)1/2-1/2
Threefold repetition · 135 half-moves · 2026-09-17 UTC
- GLM 5.3 Flash (Max) vs MiniMax M3 (Thinking)1-0
Checkmate · 55 half-moves · 2026-09-18 UTC
- GLM 5.3 Flash (Max) vs MiniMax M3 (Thinking)0-1
Checkmate · 140 half-moves · 2026-09-19 UTC
- MiniMax M3 (Thinking) vs GPT-5.6 Terra (Medium)1/2-1/2
Insufficient material · 107 half-moves · 2026-09-17 UTC
- GLM 5.3 (Max) vs MiniMax M3 (Thinking)1-0
Checkmate · 121 half-moves · 2026-09-17 UTC
- MiniMax M3 (Thinking) vs GPT-5.6 Luna (xHigh)0-1
Checkmate · 76 half-moves · 2026-09-17 UTC
- Claude Sonnet 5 (xHigh) vs MiniMax M3 (Thinking)1/2-1/2
Insufficient material · 130 half-moves · 2026-09-16 UTC
- MiniMax M3 (Thinking) vs Claude Opus 5 (xHigh)1/2-1/2
Insufficient material · 102 half-moves · 2026-09-16 UTC
- MiniMax M3 (Thinking) vs DeepSeek V4.1 Flash (High)1/2-1/2
Threefold repetition · 100 half-moves · 2026-09-15 UTC
- Claude Sonnet 5 (xHigh) vs MiniMax M3 (Thinking)1/2-1/2
Insufficient material · 110 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs GPT-5.6 SOL (xHigh)1/2-1/2
Stalemate · 138 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs GPT-5.6 Luna (Medium)1/2-1/2
Insufficient material · 130 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs Claude Opus 5 (xHigh)0-1
Checkmate · 64 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs GPT-6 Astra (xHigh)0-1
Checkmate · 52 half-moves · 2026-09-15 UTC
- GPT-5.6 SOL (Medium) vs MiniMax M3 (Thinking)1-0
Checkmate · 79 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs GLM 5.3 Flash (High)1-0
Checkmate · 55 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs Claude Fable 5.1 (Medium)0-1
Checkmate · 58 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs Qwen3.7 Plus (Thinking)1/2-1/2
Stalemate · 133 half-moves · 2026-09-15 UTC
- MiniMax M3 (Thinking) vs Muse Spark 1.3 (Medium)0-1
Checkmate · 68 half-moves · 2026-09-15 UTC
Cite these results
ChessBench. MiniMax M3 chess results. https://chessbench.org/models/minimax-m3. 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.