← All comparisons
Claude 4.5 Sonnet (Non-reasoning) vs OLMo 2 32B
Anthropic vs Allen Institute for AI — side-by-side benchmark comparison
| Claude 4.5 Sonnet (Non-reasoning) | OLMo 2 32B | |
|---|---|---|
| Intelligence Index | 37.1 | 10.6 |
| Coding Index | 33.5 | 2.7 |
| Math Index | 37.0 | 3.3 |
| Output speed (tok/s) | 54.7 | 0.0 |
| Blended price ($/1M) | $6.56 | $0.00 |
| Time to first token (s) | 1.08s | 0.00s |
| aime | — | — |
| aime 25 | 37.0% | 3.3% |
| artificial analysis coding index | 33.50 | 2.70 |
| artificial analysis intelligence index | 37.10 | 10.60 |
| artificial analysis math index | 37.00 | 3.30 |
| gpqa | 72.7% | 32.8% |
| hle | 7.1% | 3.7% |
| ifbench | 42.7% | 38.1% |
| lcr | 51.3% | 0.0% |
| livecodebench | 59.0% | 6.8% |
| math 500 | — | — |
| mmlu pro | 86.0% | 51.1% |
| scicode | 42.8% | 8.0% |
| tau2 | 70.5% | 0.0% |
| terminalbench hard | 28.8% | 0.0% |
Benchmark data from Artificial Analysis.