← All comparisons
Olmo 3.1 32B Think vs Qwen3 235B A22B (Reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Olmo 3.1 32B Think | Qwen3 235B A22B (Reasoning) | |
|---|---|---|
| Intelligence Index | 13.9 | 19.8 |
| Coding Index | 9.8 | 17.4 |
| Math Index | 77.3 | 82.0 |
| Output speed (tok/s) | 0.0 | 58.3 |
| Blended price ($/1M) | $0.00 | $2.63 |
| Time to first token (s) | 0.00s | 1.37s |
| aime | — | 84.0% |
| aime 25 | 77.3% | 82.0% |
| artificial analysis coding index | 9.80 | 17.40 |
| artificial analysis intelligence index | 13.90 | 19.80 |
| artificial analysis math index | 77.30 | 82.00 |
| gpqa | 59.1% | 70.0% |
| hle | 6.0% | 11.7% |
| ifbench | 66.0% | 38.7% |
| lcr | 0.0% | 0.0% |
| livecodebench | 69.5% | 62.2% |
| math 500 | — | 93.0% |
| mmlu pro | 76.3% | 82.8% |
| scicode | 29.3% | 39.9% |
| tau2 | 0.0% | 24.0% |
| terminalbench hard | 0.0% | 6.1% |
Benchmark data from Artificial Analysis.