← All comparisons
Gemini 3.5 Flash (minimal) vs Claude 4.1 Opus (Non-reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 3.5 Flash (minimal) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 43.3 | 36.0 |
| Coding Index | 47.1 | — |
| Math Index | — | — |
| Output speed (tok/s) | 216.5 | 44.7 |
| Blended price ($/1M) | $3.38 | $32.81 |
| Time to first token (s) | 0.81s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 47.10 | — |
| artificial analysis intelligence index | 43.30 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 82.8% | — |
| hle | 23.1% | — |
| ifbench | 47.3% | — |
| lcr | 53.3% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 48.8% | — |
| tau2 | 58.8% | — |
| terminalbench hard | 46.2% | — |
Benchmark data from Artificial Analysis.