← All comparisons
OLMo 2 32B vs Qwen3 235B A22B 2507 (Reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| OLMo 2 32B | Qwen3 235B A22B 2507 (Reasoning) | |
|---|---|---|
| Intelligence Index | 10.6 | 29.5 |
| Coding Index | 2.7 | 23.2 |
| Math Index | 3.3 | 91.0 |
| Output speed (tok/s) | 0.0 | 62.5 |
| Blended price ($/1M) | $0.00 | $0.84 |
| Time to first token (s) | 0.00s | 1.21s |
| aime | — | 94.0% |
| aime 25 | 3.3% | 91.0% |
| artificial analysis coding index | 2.70 | 23.20 |
| artificial analysis intelligence index | 10.60 | 29.50 |
| artificial analysis math index | 3.30 | 91.00 |
| gpqa | 32.8% | 79.0% |
| hle | 3.7% | 15.0% |
| ifbench | 38.1% | 51.2% |
| lcr | 0.0% | 67.0% |
| livecodebench | 6.8% | 78.8% |
| math 500 | — | 98.4% |
| mmlu pro | 51.1% | 84.3% |
| scicode | 8.0% | 42.4% |
| tau2 | 0.0% | 53.2% |
| terminalbench hard | 0.0% | 13.6% |
Benchmark data from Artificial Analysis.