MiniMax-M1 — benchmark results
MiniMax's open-weight 456B MoE reasoning model (45.9B active) using hybrid lightning attention to support a 1M-token context (June 2025). Provider: MiniMax. Released 2025-06-01. Access: Open.
Unified ELO 1497 ± 45, rank #810 of 1776 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Context Arena MRCR (2-needle) | 30.4 | AUC@1M (%) | 77.5 |
| SnakeBench | 24.1 | TrueSkill Rating | 60.6 |
| Wolfram LLM Benchmarking Project | 43.7 | Correct Functionality (%) | 57.2 |
| BenchTable | 52.3 | Total Score (%) | 56.7 |
| Chatbot Arena (Text) | 1364 | Elo | 55.6 |
| LLM2014 Logic 2025-06 | 43.83 | Median Score | 52.8 |
| AI Chess Leaderboard (Reasoning) | 653 | Elo | 48.7 |
| NYT Connections Older Models | 21.3 | Score (%) | 34.3 |
| LLM2014 Logic 2025-09 | 28.28 | Median Score | 28.9 |
| LLM2014 Logic 2025-10 | 28.28 | Median Score | 28.6 |
| AI Chess Leaderboard (Continuation) | 456 | Elo | 26.7 |
| LLM2014 Logic 2025-08 | 30.58 | Median Score | 22.7 |
Interactive version: theaggregate.ai/model?slug=minimax-m1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.