← All comparisons
Llama 3.1 Tulu3 405B vs Qwen3 4B 2507 Instruct
Allen Institute for AI vs Alibaba — side-by-side benchmark comparison
| Llama 3.1 Tulu3 405B | Qwen3 4B 2507 Instruct | |
|---|---|---|
| Intelligence Index | 14.1 | 12.9 |
| Coding Index | — | 9.0 |
| Math Index | — | 52.3 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 13.3% | — |
| aime 25 | — | 52.3% |
| artificial analysis coding index | — | 9.00 |
| artificial analysis intelligence index | 14.10 | 12.90 |
| artificial analysis math index | — | 52.30 |
| gpqa | 51.6% | 51.7% |
| hle | 3.5% | 4.7% |
| ifbench | — | 33.5% |
| lcr | — | 7.3% |
| livecodebench | 29.1% | 37.7% |
| math 500 | 77.8% | — |
| mmlu pro | 71.6% | 67.2% |
| scicode | 30.2% | 18.1% |
| tau2 | — | 26.6% |
| terminalbench hard | — | 4.5% |
Benchmark data from Artificial Analysis.