← All comparisons
GPT-5.4 nano (Non-Reasoning) vs Gemini 3.1 Flash-Lite
OpenAI vs Google — side-by-side benchmark comparison
| GPT-5.4 nano (Non-Reasoning) | Gemini 3.1 Flash-Lite | |
|---|---|---|
| Intelligence Index | 24.4 | 33.5 |
| Coding Index | 27.9 | 30.1 |
| Math Index | — | — |
| Output speed (tok/s) | 157.4 | 304.9 |
| Blended price ($/1M) | $0.46 | $0.56 |
| Time to first token (s) | 0.54s | 5.00s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 27.90 | 30.10 |
| artificial analysis intelligence index | 24.40 | 33.50 |
| artificial analysis math index | — | — |
| gpqa | 55.8% | 82.2% |
| hle | 4.2% | 16.2% |
| ifbench | 32.7% | 77.2% |
| lcr | 24.7% | 65.3% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 35.2% | 41.9% |
| tau2 | 34.8% | 31.3% |
| terminalbench hard | 24.2% | 24.2% |
Benchmark data from Artificial Analysis.