← All comparisons
Claude 4.1 Opus (Non-reasoning) vs Claude 4.5 Sonnet (Non-reasoning)
Anthropic vs Anthropic — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | Claude 4.5 Sonnet (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 36.0 | 37.1 |
| Coding Index | — | 33.5 |
| Math Index | — | 37.0 |
| Output speed (tok/s) | 44.7 | 54.7 |
| Blended price ($/1M) | $32.81 | $6.56 |
| Time to first token (s) | 1.63s | 1.08s |
| aime | — | — |
| aime 25 | — | 37.0% |
| artificial analysis coding index | — | 33.50 |
| artificial analysis intelligence index | 36.00 | 37.10 |
| artificial analysis math index | — | 37.00 |
| gpqa | — | 72.7% |
| hle | — | 7.1% |
| ifbench | — | 42.7% |
| lcr | — | 51.3% |
| livecodebench | — | 59.0% |
| math 500 | — | — |
| mmlu pro | — | 86.0% |
| scicode | — | 42.8% |
| tau2 | — | 70.5% |
| terminalbench hard | — | 28.8% |
Benchmark data from Artificial Analysis.