← All comparisons
Gemini 3 Flash Preview (Non-reasoning) vs Claude 4.1 Opus (Non-reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 3 Flash Preview (Non-reasoning) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 35.0 | 36.0 |
| Coding Index | 37.8 | — |
| Math Index | 55.7 | — |
| Output speed (tok/s) | 189.8 | 44.7 |
| Blended price ($/1M) | $1.13 | $32.81 |
| Time to first token (s) | 0.90s | 1.63s |
| aime | — | — |
| aime 25 | 55.7% | — |
| artificial analysis coding index | 37.80 | — |
| artificial analysis intelligence index | 35.00 | 36.00 |
| artificial analysis math index | 55.70 | — |
| gpqa | 81.2% | — |
| hle | 14.1% | — |
| ifbench | 55.1% | — |
| lcr | 48.0% | — |
| livecodebench | 79.7% | — |
| math 500 | — | — |
| mmlu pro | 88.2% | — |
| scicode | 49.9% | — |
| tau2 | 43.3% | — |
| terminalbench hard | 31.8% | — |
Benchmark data from Artificial Analysis.