← All comparisons
Claude 4.5 Sonnet (Reasoning) vs Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Anthropic vs Anthropic — side-by-side benchmark comparison
| Claude 4.5 Sonnet (Reasoning) | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | |
|---|---|---|
| Intelligence Index | 43.0 | 52.9 |
| Coding Index | 38.6 | 48.1 |
| Math Index | 88.0 | — |
| Output speed (tok/s) | 55.0 | 54.8 |
| Blended price ($/1M) | $6.56 | $10.94 |
| Time to first token (s) | 7.02s | 11.69s |
| aime | — | — |
| aime 25 | 88.0% | — |
| artificial analysis coding index | 38.60 | 48.10 |
| artificial analysis intelligence index | 43.00 | 52.90 |
| artificial analysis math index | 88.00 | — |
| gpqa | 83.4% | 89.6% |
| hle | 17.3% | 36.7% |
| ifbench | 57.3% | 53.1% |
| lcr | 65.7% | 70.7% |
| livecodebench | 71.4% | — |
| math 500 | — | — |
| mmlu pro | 87.5% | — |
| scicode | 44.7% | 51.9% |
| tau2 | 78.1% | 92.1% |
| terminalbench hard | 35.6% | 46.2% |
Benchmark data from Artificial Analysis.