← All comparisons
Grok 4.20 0309 v2 (Reasoning) vs Grok 4.20 0309 (Non-reasoning)
xAI vs xAI — side-by-side benchmark comparison
| Grok 4.20 0309 v2 (Reasoning) | Grok 4.20 0309 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 49.3 | 29.7 |
| Coding Index | 40.5 | 25.4 |
| Math Index | — | — |
| Output speed (tok/s) | 216.0 | 202.6 |
| Blended price ($/1M) | $3.00 | $3.00 |
| Time to first token (s) | 13.32s | 0.50s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 40.50 | 25.40 |
| artificial analysis intelligence index | 49.30 | 29.70 |
| artificial analysis math index | — | — |
| gpqa | 91.1% | 78.5% |
| hle | 32.2% | 22.5% |
| ifbench | 81.2% | 47.8% |
| lcr | 58.0% | 18.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 45.6% | 32.2% |
| tau2 | 93.0% | 69.6% |
| terminalbench hard | 37.9% | 22.0% |
Benchmark data from Artificial Analysis.