← All comparisons
Olmo 3 7B Think vs Hermes 4 - Llama-3.1 405B (Reasoning)
Allen Institute for AI vs Nous Research — side-by-side benchmark comparison
| Olmo 3 7B Think | Hermes 4 - Llama-3.1 405B (Reasoning) | |
|---|---|---|
| Intelligence Index | 9.4 | 18.6 |
| Coding Index | 7.6 | 16.0 |
| Math Index | 70.7 | 69.7 |
| Output speed (tok/s) | 0.0 | 38.6 |
| Blended price ($/1M) | $0.00 | $1.50 |
| Time to first token (s) | 0.00s | 0.79s |
| aime | — | — |
| aime 25 | 70.7% | 69.7% |
| artificial analysis coding index | 7.60 | 16.00 |
| artificial analysis intelligence index | 9.40 | 18.60 |
| artificial analysis math index | 70.70 | 69.70 |
| gpqa | 51.6% | 72.7% |
| hle | 5.7% | 10.3% |
| ifbench | 41.5% | 32.7% |
| lcr | 0.0% | 20.7% |
| livecodebench | 61.7% | 68.6% |
| math 500 | — | — |
| mmlu pro | 65.5% | 82.9% |
| scicode | 21.2% | 25.2% |
| tau2 | 0.0% | 22.2% |
| terminalbench hard | 0.8% | 11.4% |
Benchmark data from Artificial Analysis.