← All comparisons
Olmo 3.1 32B Instruct vs Qwen3 30B A3B (Non-reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Olmo 3.1 32B Instruct | Qwen3 30B A3B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 12.2 | 12.5 |
| Coding Index | 5.6 | 13.3 |
| Math Index | — | 21.7 |
| Output speed (tok/s) | 0.0 | 64.7 |
| Blended price ($/1M) | $0.00 | $0.13 |
| Time to first token (s) | 0.00s | 1.38s |
| aime | — | 26.0% |
| aime 25 | — | 21.7% |
| artificial analysis coding index | 5.60 | 13.30 |
| artificial analysis intelligence index | 12.20 | 12.50 |
| artificial analysis math index | — | 21.70 |
| gpqa | 53.9% | 51.5% |
| hle | 4.9% | 4.6% |
| ifbench | 39.2% | 31.9% |
| lcr | 0.0% | 0.0% |
| livecodebench | — | 32.2% |
| math 500 | — | 86.3% |
| mmlu pro | — | 71.0% |
| scicode | 16.7% | 26.4% |
| tau2 | 21.3% | 22.2% |
| terminalbench hard | 0.0% | 6.8% |
Benchmark data from Artificial Analysis.