← All comparisons
Gemini 3 Pro Preview (low) vs Claude 3.5 Sonnet (Oct '24)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 3 Pro Preview (low) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 41.3 | 15.9 |
| Coding Index | 39.4 | 30.2 |
| Math Index | 86.7 | — |
| 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 | 86.7% | — |
| artificial analysis coding index | 39.40 | 30.20 |
| artificial analysis intelligence index | 41.30 | 15.90 |
| artificial analysis math index | 86.70 | — |
| gpqa | 88.7% | 59.9% |
| hle | 27.6% | 3.9% |
| ifbench | 49.7% | — |
| lcr | 67.3% | — |
| livecodebench | 85.7% | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | 89.5% | 77.2% |
| scicode | 49.9% | 36.6% |
| tau2 | 68.1% | — |
| terminalbench hard | 34.1% | — |
Benchmark data from Artificial Analysis.