Claude Opus 5 vs GPT-6 Sol
Claude Opus 5 (Anthropic) and GPT-6 Sol (OpenAI) compared on price, context window, speed and independent benchmarks. Claude Opus 5 scores higher on the Artificial Analysis Intelligence Index (50.8 vs 47.5), while GPT-6 Sol is 2.5× cheaper on a blended basis. Pick Claude Opus 5 for the hardest tasks and GPT-6 Sol when cost dominates.
| Claude Opus 5 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input $/1M | $5.00 | $2.00 |
| Output $/1M | $25.0 | $10.0 |
| Blended $/1M (3:1) | $10.0 | $4.00 |
| Cached input $/1M | $0.50 | $0.20 |
| Context window | 1M | 1.1M |
| Knowledge cutoff | 2026-05 | 2026-04 |
| License | proprietary | proprietary |
| Speed (tok/s) | 57 | 107 |
| Artificial Analysis Intelligence Index | 50.8 | 47.5 |
| LMArena Elo | 1505 | — |
| GPQA Diamond | 93.2% | — |
| SWE-bench Verified | 97% | — |
| LiveCodeBench | 74.6% | — |
| MMLU-Pro | 91.6% | — |
| Humanity's Last Exam | 54.9% | 47.9% |