MiniMax M1 40k: benchmark results
MiniMax M1 open hybrid-attention reasoning model at the 40K thinking budget. Provider: MiniMax. Released 2025-06-16. Access: Open.
Aggregate Rating 1531 ± 76, rank #683 of 1656 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (OpenAI-MRCR: 2 needle 1M) | 58.6 | Score (%) | 100 |
| LLM Stats (OpenAI-MRCR: 2 needle 128k) | 76.1 | Score (%) | 87.5 |
| SpeechMap Compliance | 87.2 | % Requests Completed | 87.3 |
| AA LiveCodeBench | 65.71 | Pass@1 (%) | 73.8 |
| AA MMLU-Pro | 80.83 | Accuracy (%) | 71.6 |
| LLM Stats (LongBench v2) | 61 | Score (%) | 64.7 |
| LLM Stats (AIME 2024) | 83.3 | Score (%) | 61.4 |
| ZeroEval MATH-500 | 96 | MATH-500 Score | 50 |
| AA GPQA Diamond | 68.18 | Accuracy (%) | 45.1 |
| LLM Stats Score | 20.18 | LLM Stats Score (conservative rating) | 44.4 |
| AA Humanity's Last Exam | 7.83 | Accuracy (%) | 43.9 |
| Artificial Analysis Intelligence Index | 9.99 | Intelligence Index | 42.1 |
Interactive version: theaggregate.ai/model?slug=minimax-m1-40k · How It Works · Data refreshed daily, snapshot 2026-10-20.