← All comparisons
Molmo2-8B vs Qwen3 1.7B (Reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Molmo2-8B | Qwen3 1.7B (Reasoning) | |
|---|---|---|
| Intelligence Index | 7.3 | 8.0 |
| Coding Index | 4.4 | 1.4 |
| Math Index | — | 38.7 |
| Output speed (tok/s) | 0.0 | 136.4 |
| Blended price ($/1M) | $0.00 | $0.40 |
| Time to first token (s) | 0.00s | 0.91s |
| aime | — | 51.0% |
| aime 25 | — | 38.7% |
| artificial analysis coding index | 4.40 | 1.40 |
| artificial analysis intelligence index | 7.30 | 8.00 |
| artificial analysis math index | — | 38.70 |
| gpqa | 42.5% | 35.6% |
| hle | 4.4% | 4.8% |
| ifbench | 26.9% | 26.9% |
| lcr | 0.0% | 0.0% |
| livecodebench | — | 30.8% |
| math 500 | — | 89.4% |
| mmlu pro | — | 57.0% |
| scicode | 13.3% | 4.3% |
| tau2 | 0.0% | 26.0% |
| terminalbench hard | 0.0% | 0.0% |
Benchmark data from Artificial Analysis.