← All comparisons
Claude Sonnet 4.6 (Non-reasoning, Low Effort) vs Hermes 3 - Llama-3.1 70B
Anthropic vs Nous Research — side-by-side benchmark comparison
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Hermes 3 - Llama-3.1 70B | |
|---|---|---|
| Intelligence Index | 42.6 | 10.6 |
| Coding Index | 43.0 | — |
| Math Index | — | — |
| Output speed (tok/s) | 54.9 | 33.2 |
| Blended price ($/1M) | $6.56 | $0.30 |
| Time to first token (s) | 1.13s | 0.38s |
| aime | — | 2.3% |
| aime 25 | — | — |
| artificial analysis coding index | 43.00 | — |
| artificial analysis intelligence index | 42.60 | 10.60 |
| artificial analysis math index | — | — |
| gpqa | 79.7% | 40.1% |
| hle | 10.8% | 4.1% |
| ifbench | 42.4% | — |
| lcr | 58.7% | — |
| livecodebench | — | 18.8% |
| math 500 | — | 53.8% |
| mmlu pro | — | 57.1% |
| scicode | 44.1% | 23.1% |
| tau2 | 78.9% | — |
| terminalbench hard | 42.4% | — |
Benchmark data from Artificial Analysis.