← All comparisons
Hermes 4 - Llama-3.1 405B (Reasoning) vs Qwen3 VL 30B A3B Instruct
Nous Research vs Alibaba — side-by-side benchmark comparison
| Hermes 4 - Llama-3.1 405B (Reasoning) | Qwen3 VL 30B A3B Instruct | |
|---|---|---|
| Intelligence Index | 18.6 | 16.0 |
| Coding Index | 16.0 | 14.3 |
| Math Index | 69.7 | 72.3 |
| Output speed (tok/s) | 38.6 | 123.5 |
| Blended price ($/1M) | $1.50 | $0.30 |
| Time to first token (s) | 0.79s | 1.07s |
| aime | — | — |
| aime 25 | 69.7% | 72.3% |
| artificial analysis coding index | 16.00 | 14.30 |
| artificial analysis intelligence index | 18.60 | 16.00 |
| artificial analysis math index | 69.70 | 72.30 |
| gpqa | 72.7% | 69.5% |
| hle | 10.3% | 6.4% |
| ifbench | 32.7% | 33.1% |
| lcr | 20.7% | 23.7% |
| livecodebench | 68.6% | 47.6% |
| math 500 | — | — |
| mmlu pro | 82.9% | 76.4% |
| scicode | 25.2% | 30.8% |
| tau2 | 22.2% | 19.0% |
| terminalbench hard | 11.4% | 6.1% |
Benchmark data from Artificial Analysis.