← All comparisons
Claude 3.5 Sonnet (June '24) vs Hermes 3 - Llama-3.1 70B
Anthropic vs Nous Research — side-by-side benchmark comparison
| Claude 3.5 Sonnet (June '24) | Hermes 3 - Llama-3.1 70B | |
|---|---|---|
| Intelligence Index | 14.2 | 10.6 |
| Coding Index | 26.0 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 33.2 |
| Blended price ($/1M) | $6.56 | $0.30 |
| Time to first token (s) | 0.00s | 0.38s |
| aime | 9.7% | 2.3% |
| aime 25 | — | — |
| artificial analysis coding index | 26.00 | — |
| artificial analysis intelligence index | 14.20 | 10.60 |
| artificial analysis math index | — | — |
| gpqa | 56.0% | 40.1% |
| hle | 3.7% | 4.1% |
| ifbench | — | — |
| lcr | — | — |
| livecodebench | — | 18.8% |
| math 500 | 69.5% | 53.8% |
| mmlu pro | 75.1% | 57.1% |
| scicode | 31.6% | 23.1% |
| tau2 | — | — |
| terminalbench hard | — | — |
Benchmark data from Artificial Analysis.