← All comparisons
Claude 3.5 Sonnet (Oct '24) vs Claude Opus 4.6 (Non-reasoning, High Effort)
Anthropic vs Anthropic — side-by-side benchmark comparison
| Claude 3.5 Sonnet (Oct '24) | Claude Opus 4.6 (Non-reasoning, High Effort) | |
|---|---|---|
| Intelligence Index | 15.9 | 46.5 |
| Coding Index | 30.2 | 47.6 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 58.4 |
| Blended price ($/1M) | $6.56 | $10.94 |
| Time to first token (s) | 0.00s | 1.20s |
| aime | 15.7% | — |
| aime 25 | — | — |
| artificial analysis coding index | 30.20 | 47.60 |
| artificial analysis intelligence index | 15.90 | 46.50 |
| artificial analysis math index | — | — |
| gpqa | 59.9% | 84.0% |
| hle | 3.9% | 18.6% |
| ifbench | — | 44.6% |
| lcr | — | 58.3% |
| livecodebench | 38.1% | — |
| math 500 | 77.1% | — |
| mmlu pro | 77.2% | — |
| scicode | 36.6% | 45.7% |
| tau2 | — | 84.8% |
| terminalbench hard | — | 48.5% |
Benchmark data from Artificial Analysis.