← All comparisons
OLMo 2 32B vs Qwen2.5 Instruct 72B
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| OLMo 2 32B | Qwen2.5 Instruct 72B | |
|---|---|---|
| Intelligence Index | 10.6 | 15.6 |
| Coding Index | 2.7 | 11.9 |
| Math Index | 3.3 | 14.0 |
| Output speed (tok/s) | 0.0 | 55.4 |
| Blended price ($/1M) | $0.00 | $0.37 |
| Time to first token (s) | 0.00s | 1.23s |
| aime | — | 16.0% |
| aime 25 | 3.3% | 14.0% |
| artificial analysis coding index | 2.70 | 11.90 |
| artificial analysis intelligence index | 10.60 | 15.60 |
| artificial analysis math index | 3.30 | 14.00 |
| gpqa | 32.8% | 49.1% |
| hle | 3.7% | 4.2% |
| ifbench | 38.1% | 36.9% |
| lcr | 0.0% | 20.3% |
| livecodebench | 6.8% | 27.6% |
| math 500 | — | 85.8% |
| mmlu pro | 51.1% | 72.0% |
| scicode | 8.0% | 26.7% |
| tau2 | 0.0% | 34.5% |
| terminalbench hard | 0.0% | 4.5% |
Benchmark data from Artificial Analysis.