← All comparisons
Claude 4 Sonnet (Reasoning) vs OLMo 2 32B
Anthropic vs Allen Institute for AI — side-by-side benchmark comparison
| Claude 4 Sonnet (Reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 38.7 | 10.6 |
| Coding Index | 34.1 | 2.7 |
| Math Index | 74.3 | 3.3 |
| Output speed (tok/s) | 55.5 | 0.0 |
| Blended price ($/1M) | $6.56 | $0.00 |
| Time to first token (s) | 8.92s | 0.00s |
| aime | 77.3% | — |
| aime 25 | 74.3% | 3.3% |
| artificial analysis coding index | 34.10 | 2.70 |
| artificial analysis intelligence index | 38.70 | 10.60 |
| artificial analysis math index | 74.30 | 3.30 |
| gpqa | 77.7% | 32.8% |
| hle | 9.6% | 3.7% |
| ifbench | 54.7% | 38.1% |
| lcr | 64.7% | 0.0% |
| livecodebench | 65.5% | 6.8% |
| math 500 | 99.1% | — |
| mmlu pro | 84.2% | 51.1% |
| scicode | 40.0% | 8.0% |
| tau2 | 64.6% | 0.0% |
| terminalbench hard | 31.1% | 0.0% |
Benchmark data from Artificial Analysis.