← All comparisons
Hermes 4 - Llama-3.1 70B (Non-reasoning) vs Qwen3.5 122B A10B (Non-reasoning)
Nous Research vs Alibaba — side-by-side benchmark comparison
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | Qwen3.5 122B A10B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 12.6 | 35.9 |
| Coding Index | 9.2 | 31.6 |
| Math Index | 11.3 | — |
| Output speed (tok/s) | 94.3 | 165.9 |
| Blended price ($/1M) | $0.20 | $1.10 |
| Time to first token (s) | 0.61s | 1.06s |
| aime | — | — |
| aime 25 | 11.3% | — |
| artificial analysis coding index | 9.20 | 31.60 |
| artificial analysis intelligence index | 12.60 | 35.90 |
| artificial analysis math index | 11.30 | — |
| gpqa | 49.1% | 82.7% |
| hle | 3.6% | 14.8% |
| ifbench | 29.0% | 50.8% |
| lcr | 2.0% | 56.0% |
| livecodebench | 26.9% | — |
| math 500 | — | — |
| mmlu pro | 66.4% | — |
| scicode | 27.7% | 35.6% |
| tau2 | 21.6% | 84.5% |
| terminalbench hard | 0.0% | 29.5% |
Benchmark data from Artificial Analysis.