← All comparisons
Gemini 2.5 Flash Preview (Sep '25) (Reasoning) vs Claude 4.5 Sonnet (Reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | Claude 4.5 Sonnet (Reasoning) | |
|---|---|---|
| Intelligence Index | 31.1 | 43.0 |
| Coding Index | 24.6 | 38.6 |
| Math Index | 78.3 | 88.0 |
| Output speed (tok/s) | 0.0 | 55.0 |
| Blended price ($/1M) | $0.00 | $6.56 |
| Time to first token (s) | 0.00s | 7.02s |
| aime | — | — |
| aime 25 | 78.3% | 88.0% |
| artificial analysis coding index | 24.60 | 38.60 |
| artificial analysis intelligence index | 31.10 | 43.00 |
| artificial analysis math index | 78.30 | 88.00 |
| gpqa | 79.3% | 83.4% |
| hle | 12.7% | 17.3% |
| ifbench | 52.3% | 57.3% |
| lcr | 64.3% | 65.7% |
| livecodebench | 71.3% | 71.4% |
| math 500 | — | — |
| mmlu pro | 84.2% | 87.5% |
| scicode | 40.5% | 44.7% |
| tau2 | 45.6% | 78.1% |
| terminalbench hard | 16.7% | 35.6% |
Benchmark data from Artificial Analysis.