← All comparisons
Olmo 3 7B Instruct vs Hermes 4 - Llama-3.1 70B (Reasoning)
Allen Institute for AI vs Nous Research — side-by-side benchmark comparison
| Olmo 3 7B Instruct | Hermes 4 - Llama-3.1 70B (Reasoning) | |
|---|---|---|
| Intelligence Index | 8.1 | 16.0 |
| Coding Index | 3.4 | 14.4 |
| Math Index | 41.3 | 68.7 |
| Output speed (tok/s) | 0.0 | 92.8 |
| Blended price ($/1M) | $0.13 | $0.20 |
| Time to first token (s) | 0.00s | 0.64s |
| aime | — | — |
| aime 25 | 41.3% | 68.7% |
| artificial analysis coding index | 3.40 | 14.40 |
| artificial analysis intelligence index | 8.10 | 16.00 |
| artificial analysis math index | 41.30 | 68.70 |
| gpqa | 40.0% | 69.9% |
| hle | 5.8% | 7.9% |
| ifbench | 32.8% | 31.3% |
| lcr | 0.0% | 6.7% |
| livecodebench | 26.6% | 65.3% |
| math 500 | — | — |
| mmlu pro | 52.2% | 81.1% |
| scicode | 10.3% | 34.1% |
| tau2 | 12.6% | 22.5% |
| terminalbench hard | 0.0% | 4.5% |
Benchmark data from Artificial Analysis.