← All comparisons
Olmo 3.1 32B Think vs Claude 4.1 Opus (Non-reasoning)
Allen Institute for AI vs Anthropic — side-by-side benchmark comparison
| Olmo 3.1 32B Think | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 13.9 | 36.0 |
| Coding Index | 9.8 | — |
| Math Index | 77.3 | — |
| Output speed (tok/s) | 0.0 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 1.63s |
| aime | — | — |
| aime 25 | 77.3% | — |
| artificial analysis coding index | 9.80 | — |
| artificial analysis intelligence index | 13.90 | 36.00 |
| artificial analysis math index | 77.30 | — |
| gpqa | 59.1% | — |
| hle | 6.0% | — |
| ifbench | 66.0% | — |
| lcr | 0.0% | — |
| livecodebench | 69.5% | — |
| math 500 | — | — |
| mmlu pro | 76.3% | — |
| scicode | 29.3% | — |
| tau2 | 0.0% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.