← All comparisons
Qwen3.5 122B A10B (Non-reasoning) vs Grok 4.20 0309 (Non-reasoning)
Alibaba vs xAI — side-by-side benchmark comparison
| Qwen3.5 122B A10B (Non-reasoning) | Grok 4.20 0309 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 35.9 | 29.7 |
| Coding Index | 31.6 | 25.4 |
| Math Index | — | — |
| Output speed (tok/s) | 165.9 | 202.6 |
| Blended price ($/1M) | $1.10 | $3.00 |
| Time to first token (s) | 1.06s | 0.50s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 31.60 | 25.40 |
| artificial analysis intelligence index | 35.90 | 29.70 |
| artificial analysis math index | — | — |
| gpqa | 82.7% | 78.5% |
| hle | 14.8% | 22.5% |
| ifbench | 50.8% | 47.8% |
| lcr | 56.0% | 18.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 35.6% | 32.2% |
| tau2 | 84.5% | 69.6% |
| terminalbench hard | 29.5% | 22.0% |
Benchmark data from Artificial Analysis.