← All comparisons
Qwen3.6 35B A3B (Non-reasoning) vs Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)
Alibaba vs NVIDIA — side-by-side benchmark comparison
| Qwen3.6 35B A3B (Non-reasoning) | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | |
|---|---|---|
| Intelligence Index | 31.5 | 14.4 |
| Coding Index | 17.6 | — |
| Math Index | — | 50.0 |
| Output speed (tok/s) | 169.5 | 0.0 |
| Blended price ($/1M) | $0.84 | $0.00 |
| Time to first token (s) | 1.47s | 0.00s |
| aime | — | 70.7% |
| aime 25 | — | 50.0% |
| artificial analysis coding index | 17.60 | — |
| artificial analysis intelligence index | 31.50 | 14.40 |
| artificial analysis math index | — | 50.00 |
| gpqa | 81.7% | 40.8% |
| hle | 12.5% | 5.1% |
| ifbench | 36.2% | 25.5% |
| lcr | 56.7% | 0.0% |
| livecodebench | — | 49.3% |
| math 500 | — | 94.7% |
| mmlu pro | — | 55.6% |
| scicode | 1.3% | 10.1% |
| tau2 | 85.1% | 11.7% |
| terminalbench hard | 25.8% | — |
Benchmark data from Artificial Analysis.