← All comparisons
Grok 4.3 (medium) vs Qwen3 30B A3B (Reasoning)
xAI vs Alibaba — side-by-side benchmark comparison
| Grok 4.3 (medium) | Qwen3 30B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 48.8 | 15.3 |
| Coding Index | 35.1 | 11.0 |
| Math Index | — | 72.3 |
| Output speed (tok/s) | 112.5 | 64.1 |
| Blended price ($/1M) | $1.56 | $0.18 |
| Time to first token (s) | 17.68s | 1.18s |
| aime | — | 75.3% |
| aime 25 | — | 72.3% |
| artificial analysis coding index | 35.10 | 11.00 |
| artificial analysis intelligence index | 48.80 | 15.30 |
| artificial analysis math index | — | 72.30 |
| gpqa | 89.0% | 61.6% |
| hle | 28.1% | 6.6% |
| ifbench | 83.3% | 41.5% |
| lcr | 65.0% | 0.0% |
| livecodebench | — | 50.6% |
| math 500 | — | 95.9% |
| mmlu pro | — | 77.7% |
| scicode | 44.6% | 28.5% |
| tau2 | 91.2% | 26.0% |
| terminalbench hard | 30.3% | 2.3% |
Benchmark data from Artificial Analysis.