← All comparisons
Qwen3 Next 80B A3B (Reasoning) vs GPT-4.1 nano
Alibaba vs OpenAI — side-by-side benchmark comparison
| Qwen3 Next 80B A3B (Reasoning) | GPT-4.1 nano | |
|---|---|---|
| Intelligence Index | 26.7 | 13.0 |
| Coding Index | 19.5 | 11.2 |
| Math Index | 84.3 | 24.0 |
| Output speed (tok/s) | 149.4 | 178.9 |
| Blended price ($/1M) | $1.88 | $0.17 |
| Time to first token (s) | 1.23s | 0.40s |
| aime | — | 23.7% |
| aime 25 | 84.3% | 24.0% |
| artificial analysis coding index | 19.50 | 11.20 |
| artificial analysis intelligence index | 26.70 | 13.00 |
| artificial analysis math index | 84.30 | 24.00 |
| gpqa | 75.9% | 51.2% |
| hle | 11.7% | 3.9% |
| ifbench | 60.7% | 32.0% |
| lcr | 60.3% | 17.0% |
| livecodebench | 78.4% | 32.6% |
| math 500 | — | 84.8% |
| mmlu pro | 82.4% | 65.7% |
| scicode | 38.8% | 25.9% |
| tau2 | 41.5% | 17.3% |
| terminalbench hard | 9.8% | 3.8% |
Benchmark data from Artificial Analysis.