← All comparisons
Olmo 3 7B Instruct vs Qwen3 235B A22B (Non-reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Olmo 3 7B Instruct | Qwen3 235B A22B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 8.1 | 17.0 |
| Coding Index | 3.4 | 14.0 |
| Math Index | 41.3 | 23.7 |
| Output speed (tok/s) | 0.0 | 60.8 |
| Blended price ($/1M) | $0.13 | $0.79 |
| Time to first token (s) | 0.00s | 1.30s |
| aime | — | 32.7% |
| aime 25 | 41.3% | 23.7% |
| artificial analysis coding index | 3.40 | 14.00 |
| artificial analysis intelligence index | 8.10 | 17.00 |
| artificial analysis math index | 41.30 | 23.70 |
| gpqa | 40.0% | 61.3% |
| hle | 5.8% | 4.7% |
| ifbench | 32.8% | 36.6% |
| lcr | 0.0% | 0.0% |
| livecodebench | 26.6% | 34.3% |
| math 500 | — | 90.2% |
| mmlu pro | 52.2% | 76.2% |
| scicode | 10.3% | 29.9% |
| tau2 | 12.6% | 27.2% |
| terminalbench hard | 0.0% | 6.1% |
Benchmark data from Artificial Analysis.