← All comparisons
OLMo 2 7B vs Qwen3 VL 235B A22B (Reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| OLMo 2 7B | Qwen3 VL 235B A22B (Reasoning) | |
|---|---|---|
| Intelligence Index | 9.3 | 27.6 |
| Coding Index | 1.2 | 20.9 |
| Math Index | 0.7 | 88.3 |
| Output speed (tok/s) | 0.0 | 35.6 |
| Blended price ($/1M) | $0.00 | $2.17 |
| Time to first token (s) | 0.00s | 5.14s |
| aime | — | — |
| aime 25 | 0.7% | 88.3% |
| artificial analysis coding index | 1.20 | 20.90 |
| artificial analysis intelligence index | 9.30 | 27.60 |
| artificial analysis math index | 70.0% | 88.30 |
| gpqa | 28.8% | 77.2% |
| hle | 5.5% | 10.1% |
| ifbench | 24.4% | 56.5% |
| lcr | 0.0% | 58.7% |
| livecodebench | 4.1% | 64.6% |
| math 500 | — | — |
| mmlu pro | 28.2% | 83.6% |
| scicode | 3.7% | 39.9% |
| tau2 | 0.0% | 54.1% |
| terminalbench hard | 0.0% | 11.4% |
Benchmark data from Artificial Analysis.