← All comparisons
Olmo 3.1 32B Instruct vs Qwen3 1.7B (Non-reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | Qwen3 1.7B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 12.2 | 6.8 |
| Coding Index | 5.6 | 2.3 |
| Math Index | — | 7.3 |
| Output speed (tok/s) | 0.0 | 137.6 |
| Blended price ($/1M) | $0.00 | $0.19 |
| Time to first token (s) | 0.00s | 0.93s |
| aime | — | 9.7% |
| aime 25 | — | 7.3% |
| artificial analysis coding index | 5.60 | 2.30 |
| artificial analysis intelligence index | 12.20 | 6.80 |
| artificial analysis math index | — | 7.30 |
| gpqa | 53.9% | 28.3% |
| hle | 4.9% | 5.2% |
| ifbench | 39.2% | 21.1% |
| lcr | 0.0% | 0.0% |
| livecodebench | — | 12.6% |
| math 500 | — | 71.7% |
| mmlu pro | — | 41.1% |
| scicode | 16.7% | 6.9% |
| tau2 | 21.3% | 21.6% |
| terminalbench hard | 0.0% | 0.0% |
Benchmark data from Artificial Analysis.