← All comparisons
Gemini 2.0 Flash (Feb '25) vs Claude 3.5 Sonnet (Oct '24)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 2.0 Flash (Feb '25) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 18.5 | 15.9 |
| Coding Index | 13.6 | 30.2 |
| Math Index | 21.7 | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.26 | $6.56 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 33.0% | 15.7% |
| aime 25 | 21.7% | — |
| artificial analysis coding index | 13.60 | 30.20 |
| artificial analysis intelligence index | 18.50 | 15.90 |
| artificial analysis math index | 21.70 | — |
| gpqa | 62.3% | 59.9% |
| hle | 5.3% | 3.9% |
| ifbench | 40.2% | — |
| lcr | 28.3% | — |
| livecodebench | 33.4% | 38.1% |
| math 500 | 93.0% | 77.1% |
| mmlu pro | 77.9% | 77.2% |
| scicode | 33.3% | 36.6% |
| tau2 | 29.5% | — |
| terminalbench hard | 3.8% | — |
Benchmark data from Artificial Analysis.