← All comparisons
Claude 4.5 Haiku (Reasoning) vs DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
Anthropic vs Nous Research — side-by-side benchmark comparison
| Claude 4.5 Haiku (Reasoning) | DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 37.1 | 10.9 |
| Coding Index | 32.6 | — |
| Math Index | 83.7 | — |
| Output speed (tok/s) | 142.2 | 0.0 |
| Blended price ($/1M) | $2.19 | $0.00 |
| Time to first token (s) | 10.48s | 0.00s |
| aime | — | 4.7% |
| aime 25 | 83.7% | — |
| artificial analysis coding index | 32.60 | — |
| artificial analysis intelligence index | 37.10 | 10.90 |
| artificial analysis math index | 83.70 | — |
| gpqa | 67.2% | 38.2% |
| hle | 9.7% | 3.9% |
| ifbench | 54.3% | — |
| lcr | 70.3% | — |
| livecodebench | 61.5% | 19.5% |
| math 500 | — | 59.5% |
| mmlu pro | 76.0% | 58.0% |
| scicode | 43.3% | 22.8% |
| tau2 | 54.7% | — |
| terminalbench hard | 27.3% | — |
Benchmark data from Artificial Analysis.