← All comparisons
Claude Opus 4.5 (Reasoning) vs OLMo 2 32B
Anthropic vs Allen Institute for AI — side-by-side benchmark comparison
| Claude Opus 4.5 (Reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 49.7 | 10.6 |
| Coding Index | 47.8 | 2.7 |
| Math Index | 91.3 | 3.3 |
| Output speed (tok/s) | 73.2 | 0.0 |
| Blended price ($/1M) | $10.94 | $0.00 |
| Time to first token (s) | 11.69s | 0.00s |
| aime | — | — |
| aime 25 | 91.3% | 3.3% |
| artificial analysis coding index | 47.80 | 2.70 |
| artificial analysis intelligence index | 49.70 | 10.60 |
| artificial analysis math index | 91.30 | 3.30 |
| gpqa | 86.6% | 32.8% |
| hle | 28.4% | 3.7% |
| ifbench | 58.0% | 38.1% |
| lcr | 74.0% | 0.0% |
| livecodebench | 87.1% | 6.8% |
| math 500 | — | — |
| mmlu pro | 89.5% | 51.1% |
| scicode | 49.5% | 8.0% |
| tau2 | 89.5% | 0.0% |
| terminalbench hard | 47.0% | 0.0% |
Benchmark data from Artificial Analysis.