← All comparisons
GPT-3.5 Turbo vs Gemini 2.0 Pro Experimental (Feb '25)
OpenAI vs Google — side-by-side benchmark comparison
| GPT-3.5 Turbo | Gemini 2.0 Pro Experimental (Feb '25) | |
|---|---|---|
| Intelligence Index | 9.0 | 18.1 |
| Coding Index | 10.7 | 25.5 |
| Math Index | — | — |
| Output speed (tok/s) | 116.9 | 0.0 |
| Blended price ($/1M) | $0.75 | $0.00 |
| Time to first token (s) | 0.56s | 0.00s |
| aime | — | 36.0% |
| aime 25 | — | — |
| artificial analysis coding index | 10.70 | 25.50 |
| artificial analysis intelligence index | 9.00 | 18.10 |
| artificial analysis math index | — | — |
| gpqa | 29.7% | 62.2% |
| hle | — | 6.8% |
| ifbench | — | — |
| lcr | — | — |
| livecodebench | — | 34.7% |
| math 500 | 44.1% | 92.3% |
| mmlu pro | 46.2% | 80.5% |
| scicode | — | 31.3% |
| tau2 | — | — |
| terminalbench hard | — | — |
Benchmark data from Artificial Analysis.