MiniMax M1 scores 14.6 on the Respan Index (#123), ahead of Claude 3.5 Sonnet at 14.4 (#125). MiniMax M1 leads on 3 of the 4 benchmarks both report. MiniMax M1 has the larger context window (1M tokens).
| Benchmark | Claude 3.5 Sonnet | MiniMax M1 |
|---|---|---|
| GPQA Diamond | 55.3% | 70% |
| LMArena Elo | 1374 | 1364 |
| AIME 2025 | 3.3% | 76.9% |
| SWE-bench Verified | 49% | 56% |
Higher is better. Each score links to where it was published.
* Estimated: no published scores in that category. How the Respan Index works