← All comparisons
Claude 3.5 Haiku vs Mistral Large 2 (Nov '24)
Anthropic vs Mistral — side-by-side benchmark comparison
| Claude 3.5 Haiku | Mistral Large 2 (Nov '24) | |
|---|---|---|
| Intelligence Index | 18.7 | 15.1 |
| Coding Index | 10.7 | 13.8 |
| Math Index | — | 14.0 |
| Output speed (tok/s) | 0.0 | 32.2 |
| Blended price ($/1M) | $1.75 | $3.00 |
| Time to first token (s) | 0.00s | 0.60s |
| aime | 3.3% | 11.0% |
| aime 25 | — | 14.0% |
| artificial analysis coding index | 10.70 | 13.80 |
| artificial analysis intelligence index | 18.70 | 15.10 |
| artificial analysis math index | — | 14.00 |
| gpqa | 40.8% | 48.6% |
| hle | 3.5% | 4.0% |
| ifbench | 42.8% | 31.2% |
| lcr | 23.3% | 5.3% |
| livecodebench | 31.4% | 29.3% |
| math 500 | 72.1% | 73.6% |
| mmlu pro | 63.4% | 69.7% |
| scicode | 27.4% | 29.2% |
| tau2 | 24.6% | 30.7% |
| terminalbench hard | 2.3% | 6.1% |
Benchmark data from Artificial Analysis.