← All comparisons
Hermes 4 - Llama-3.1 405B (Non-reasoning) vs Grok 4.20 0309 (Non-reasoning)
Nous Research vs xAI — side-by-side benchmark comparison
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | Grok 4.20 0309 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 17.6 | 29.7 |
| Coding Index | 18.1 | 25.4 |
| Math Index | 15.3 | — |
| Output speed (tok/s) | 40.8 | 202.6 |
| Blended price ($/1M) | $1.50 | $3.00 |
| Time to first token (s) | 0.73s | 0.50s |
| aime | — | — |
| aime 25 | 15.3% | — |
| artificial analysis coding index | 18.10 | 25.40 |
| artificial analysis intelligence index | 17.60 | 29.70 |
| artificial analysis math index | 15.30 | — |
| gpqa | 53.6% | 78.5% |
| hle | 4.2% | 22.5% |
| ifbench | 34.8% | 47.8% |
| lcr | 20.0% | 18.0% |
| livecodebench | 54.6% | — |
| math 500 | — | — |
| mmlu pro | 72.9% | — |
| scicode | 34.6% | 32.2% |
| tau2 | 26.6% | 69.6% |
| terminalbench hard | 9.8% | 22.0% |
Benchmark data from Artificial Analysis.