← All comparisons
Olmo 3 7B Think vs Qwen3.6 27B (Reasoning)
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Olmo 3 7B Think | Qwen3.6 27B (Reasoning) | |
|---|---|---|
| Intelligence Index | 9.4 | 45.8 |
| Coding Index | 7.6 | 36.5 |
| Math Index | 70.7 | — |
| Output speed (tok/s) | 0.0 | 57.4 |
| Blended price ($/1M) | $0.00 | $1.35 |
| Time to first token (s) | 0.00s | 1.46s |
| aime | — | — |
| aime 25 | 70.7% | — |
| artificial analysis coding index | 7.60 | 36.50 |
| artificial analysis intelligence index | 9.40 | 45.80 |
| artificial analysis math index | 70.70 | — |
| gpqa | 51.6% | 84.2% |
| hle | 5.7% | 21.6% |
| ifbench | 41.5% | 67.6% |
| lcr | 0.0% | 68.7% |
| livecodebench | 61.7% | — |
| math 500 | — | — |
| mmlu pro | 65.5% | — |
| scicode | 21.2% | 39.8% |
| tau2 | 0.0% | 94.2% |
| terminalbench hard | 0.8% | 34.8% |
Benchmark data from Artificial Analysis.