← All comparisons
Gemini 3 Pro Preview (high) vs Claude 3.5 Sonnet (Oct '24)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 3 Pro Preview (high) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 48.4 | 15.9 |
| Coding Index | 46.5 | 30.2 |
| Math Index | 95.7 | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $4.50 | $6.56 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | 15.7% |
| aime 25 | 95.7% | — |
| artificial analysis coding index | 46.50 | 30.20 |
| artificial analysis intelligence index | 48.40 | 15.90 |
| artificial analysis math index | 95.70 | — |
| gpqa | 90.8% | 59.9% |
| hle | 37.2% | 3.9% |
| ifbench | 70.4% | — |
| lcr | 70.7% | — |
| livecodebench | 91.7% | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | 89.8% | 77.2% |
| scicode | 56.1% | 36.6% |
| tau2 | 87.1% | — |
| terminalbench hard | 41.7% | — |
Benchmark data from Artificial Analysis.