← All comparisons
Claude 3.5 Sonnet (June '24) vs MiniMax-M2
Anthropic vs MiniMax — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | MiniMax-M2 | |
|---|---|---|
| Intelligence Index | 14.2 | 36.1 |
| Coding Index | 26.0 | 29.2 |
| Math Index | — | 78.3 |
| Output speed (tok/s) | 0.0 | 116.0 |
| Blended price ($/1M) | $6.56 | $0.53 |
| Time to first token (s) | 0.00s | 0.99s |
| aime | 9.7% | — |
| aime 25 | — | 78.3% |
| artificial analysis coding index | 26.00 | 29.20 |
| artificial analysis intelligence index | 14.20 | 36.10 |
| artificial analysis math index | — | 78.30 |
| gpqa | 56.0% | 77.7% |
| hle | 3.7% | 12.5% |
| ifbench | — | 72.3% |
| lcr | — | 61.0% |
| livecodebench | — | 82.6% |
| math 500 | 69.5% | — |
| mmlu pro | 75.1% | 82.0% |
| scicode | 31.6% | 36.1% |
| tau2 | — | 86.8% |
| terminalbench hard | — | 25.8% |
Benchmark data from Artificial Analysis.