← All comparisons
Grok 3 mini Reasoning (high) vs Hermes 3 - Llama-3.1 70B
xAI vs Nous Research — side-by-side benchmark comparison
| Grok 3 mini Reasoning (high) | Hermes 3 - Llama-3.1 70B | |
|---|---|---|
| Intelligence Index | 32.1 | 10.6 |
| Coding Index | 25.2 | — |
| Math Index | 84.7 | — |
| Output speed (tok/s) | 56.8 | 33.2 |
| Blended price ($/1M) | $0.35 | $0.30 |
| Time to first token (s) | 0.42s | 0.38s |
| aime | 93.3% | 2.3% |
| aime 25 | 84.7% | — |
| artificial analysis coding index | 25.20 | — |
| artificial analysis intelligence index | 32.10 | 10.60 |
| artificial analysis math index | 84.70 | — |
| gpqa | 79.1% | 40.1% |
| hle | 11.1% | 4.1% |
| ifbench | 45.9% | — |
| lcr | 50.3% | — |
| livecodebench | 69.6% | 18.8% |
| math 500 | 99.2% | 53.8% |
| mmlu pro | 82.8% | 57.1% |
| scicode | 40.6% | 23.1% |
| tau2 | 90.4% | — |
| terminalbench hard | 17.4% | — |
Benchmark data from Artificial Analysis.