← All comparisons
Molmo 7B-D vs Qwen3.5 0.8B (Non-reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Molmo 7B-D | Qwen3.5 0.8B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 9.2 | 9.9 |
| Coding Index | 1.2 | 1.0 |
| Math Index | 0.0 | — |
| Output speed (tok/s) | 0.0 | 96.3 |
| Blended price ($/1M) | $0.00 | $0.02 |
| Time to first token (s) | 0.00s | 0.26s |
| aime | — | — |
| aime 25 | 0.0% | — |
| artificial analysis coding index | 1.20 | 100.0% |
| artificial analysis intelligence index | 9.20 | 9.90 |
| artificial analysis math index | 0.0% | — |
| gpqa | 24.0% | 23.6% |
| hle | 5.1% | 4.9% |
| ifbench | 19.7% | 21.6% |
| lcr | 0.0% | 6.7% |
| livecodebench | 3.9% | — |
| math 500 | — | — |
| mmlu pro | 37.1% | — |
| scicode | 3.6% | 2.9% |
| tau2 | 0.0% | 65.2% |
| terminalbench hard | 0.0% | 0.0% |
Benchmark data from Artificial Analysis.