← All comparisons
Gemini 3.1 Pro Preview vs Claude 4.1 Opus (Non-reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemini 3.1 Pro Preview | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 57.2 | 36.0 |
| Coding Index | 55.5 | — |
| Math Index | — | — |
| Output speed (tok/s) | 136.8 | 44.7 |
| Blended price ($/1M) | $4.50 | $32.81 |
| Time to first token (s) | 25.68s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 55.50 | — |
| artificial analysis intelligence index | 57.20 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 94.1% | — |
| hle | 44.7% | — |
| ifbench | 77.1% | — |
| lcr | 72.7% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 58.9% | — |
| tau2 | 95.6% | — |
| terminalbench hard | 53.8% | — |
Benchmark data from Artificial Analysis.