← All comparisons
Claude 4.1 Opus (Reasoning) vs Claude 4.5 Sonnet (Non-reasoning)
Anthropic vs Anthropic — side-by-side benchmark comparison
| Claude 4.1 Opus (Reasoning) | Claude 4.5 Sonnet (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 42.0 | 37.1 |
| Coding Index | 36.5 | 33.5 |
| Math Index | 80.3 | 37.0 |
| Output speed (tok/s) | 44.5 | 54.7 |
| Blended price ($/1M) | $32.81 | $6.56 |
| Time to first token (s) | 8.55s | 1.08s |
| aime | — | — |
| aime 25 | 80.3% | 37.0% |
| artificial analysis coding index | 36.50 | 33.50 |
| artificial analysis intelligence index | 42.00 | 37.10 |
| artificial analysis math index | 80.30 | 37.00 |
| gpqa | 80.9% | 72.7% |
| hle | 11.9% | 7.1% |
| ifbench | 55.4% | 42.7% |
| lcr | 66.3% | 51.3% |
| livecodebench | 65.4% | 59.0% |
| math 500 | — | — |
| mmlu pro | 88.0% | 86.0% |
| scicode | 40.9% | 42.8% |
| tau2 | 71.4% | 70.5% |
| terminalbench hard | 34.3% | 28.8% |
Benchmark data from Artificial Analysis.