← All comparisons
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Qwen3.6 27B (Non-reasoning)
NVIDIA vs Alibaba — side-by-side benchmark comparison
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | Qwen3.6 27B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 24.3 | 37.1 |
| Coding Index | 19.0 | 26.6 |
| Math Index | 91.0 | — |
| Output speed (tok/s) | 122.8 | 60.7 |
| Blended price ($/1M) | $0.10 | $1.35 |
| Time to first token (s) | 0.83s | 1.55s |
| aime | — | — |
| aime 25 | 91.0% | — |
| artificial analysis coding index | 19.00 | 26.60 |
| artificial analysis intelligence index | 24.30 | 37.10 |
| artificial analysis math index | 91.00 | — |
| gpqa | 75.7% | 82.9% |
| hle | 10.2% | 13.6% |
| ifbench | 71.1% | 45.7% |
| lcr | 33.7% | 55.0% |
| livecodebench | 74.1% | — |
| math 500 | — | — |
| mmlu pro | 79.4% | — |
| scicode | 29.6% | 37.3% |
| tau2 | 40.9% | 93.6% |
| terminalbench hard | 13.6% | 21.2% |
Benchmark data from Artificial Analysis.