← All comparisons
Grok 4.3 (Non-reasoning) vs Gemini 2.5 Flash-Lite (Non-reasoning)
xAI vs Google — side-by-side benchmark comparison
| Grok 4.3 (Non-reasoning) | Gemini 2.5 Flash-Lite (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 31.0 | 12.7 |
| Coding Index | 25.1 | 7.4 |
| Math Index | — | 35.3 |
| Output speed (tok/s) | 143.7 | 294.2 |
| Blended price ($/1M) | $1.56 | $0.17 |
| Time to first token (s) | 0.42s | 0.34s |
| aime | — | 50.0% |
| aime 25 | — | 35.3% |
| artificial analysis coding index | 25.10 | 7.40 |
| artificial analysis intelligence index | 31.00 | 12.70 |
| artificial analysis math index | — | 35.30 |
| gpqa | 65.8% | 47.4% |
| hle | 6.5% | 3.7% |
| ifbench | 47.6% | 31.5% |
| lcr | 24.7% | 31.3% |
| livecodebench | — | 40.0% |
| math 500 | — | 92.6% |
| mmlu pro | — | 72.4% |
| scicode | 37.4% | 17.7% |
| tau2 | 65.8% | 19.0% |
| terminalbench hard | 18.9% | 2.3% |
Benchmark data from Artificial Analysis.