← All comparisons
Llama 3.2 Instruct 3B vs OLMo 2 7B
Meta vs Allen Institute for AI — side-by-side benchmark comparison
| Llama 3.2 Instruct 3B | OLMo 2 7B | |
|---|---|---|
| Intelligence Index | 9.7 | 9.3 |
| Coding Index | — | 1.2 |
| Math Index | 3.3 | 0.7 |
| Output speed (tok/s) | 52.7 | 0.0 |
| Blended price ($/1M) | $0.15 | $0.00 |
| Time to first token (s) | 0.65s | 0.00s |
| aime | 6.7% | — |
| aime 25 | 3.3% | 0.7% |
| artificial analysis coding index | — | 1.20 |
| artificial analysis intelligence index | 9.70 | 9.30 |
| artificial analysis math index | 3.30 | 70.0% |
| gpqa | 25.5% | 28.8% |
| hle | 5.2% | 5.5% |
| ifbench | 26.2% | 24.4% |
| lcr | 2.0% | 0.0% |
| livecodebench | 8.3% | 4.1% |
| math 500 | 48.9% | — |
| mmlu pro | 34.7% | 28.2% |
| scicode | 5.2% | 3.7% |
| tau2 | 21.1% | 0.0% |
| terminalbench hard | — | 0.0% |
Benchmark data from Artificial Analysis.