← All comparisons
Llama 3.1 Instruct 70B vs OLMo 2 7B
Meta vs Allen Institute for AI — side-by-side benchmark comparison
| Llama 3.1 Instruct 70B | OLMo 2 7B | |
|---|---|---|
| Intelligence Index | 12.5 | 9.3 |
| Coding Index | 10.9 | 1.2 |
| Math Index | 4.0 | 0.7 |
| Output speed (tok/s) | 35.3 | 0.0 |
| Blended price ($/1M) | $0.56 | $0.00 |
| Time to first token (s) | 0.54s | 0.00s |
| aime | 17.3% | — |
| aime 25 | 4.0% | 0.7% |
| artificial analysis coding index | 10.90 | 1.20 |
| artificial analysis intelligence index | 12.50 | 9.30 |
| artificial analysis math index | 4.00 | 70.0% |
| gpqa | 40.9% | 28.8% |
| hle | 4.6% | 5.5% |
| ifbench | 34.4% | 24.4% |
| lcr | 6.3% | 0.0% |
| livecodebench | 23.2% | 4.1% |
| math 500 | 64.9% | — |
| mmlu pro | 67.6% | 28.2% |
| scicode | 26.7% | 3.7% |
| tau2 | 15.2% | 0.0% |
| terminalbench hard | 3.0% | 0.0% |
Benchmark data from Artificial Analysis.