← All comparisons
OLMo 2 32B vs Qwen2.5 Max
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| OLMo 2 32B | Qwen2.5 Max | |
|---|---|---|
| Intelligence Index | 10.6 | 16.3 |
| Coding Index | 2.7 | — |
| Math Index | 3.3 | — |
| Output speed (tok/s) | 0.0 | 45.0 |
| Blended price ($/1M) | $0.00 | $2.80 |
| Time to first token (s) | 0.00s | 1.16s |
| aime | — | 23.3% |
| aime 25 | 3.3% | — |
| artificial analysis coding index | 2.70 | — |
| artificial analysis intelligence index | 10.60 | 16.30 |
| artificial analysis math index | 3.30 | — |
| gpqa | 32.8% | 58.7% |
| hle | 3.7% | 4.5% |
| ifbench | 38.1% | — |
| lcr | 0.0% | — |
| livecodebench | 6.8% | 35.9% |
| math 500 | — | 83.5% |
| mmlu pro | 51.1% | 76.2% |
| scicode | 8.0% | 33.7% |
| tau2 | 0.0% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.