Claude Opus 4.6 vs Claude Sonnet 4.6: Specs & Benchmark Comparison
| Characteristic | Claude Opus 4.6 | Claude Sonnet 4.6 |
|---|---|---|
| Company | Anthropic | Anthropic |
| Release Date | February 4, 2026 | February 17, 2026 |
| Parameters | — | — |
| Multimodal | Yes | Yes |
| Context (input) | 1.0M | 200K |
| Context (output) | 128K | 64K |
| Input Price / 1M | $5.00 | $3.00 |
| Output Price / 1M | $25.00 | $15.00 |
| Average Score | 0.8 | 0.7 |
| Benchmarks | ||
| ARC-AGI v2 | 0.7 | 0.6 |
| Humanity's Last Exam | 0.5 | 0.5 |
| SWE-Bench Verified | 0.8 | 0.8 |
| GPQA | 0.9 | 0.9 |
| CharXiv-R | 0.7 | 0.7 |
Visual Benchmark Comparison
Verdict
Both models show equal results — the choice depends on your specific use case.
Both models show comparable average scores: Claude Opus 4.6 — 0.8, Claude Sonnet 4.6 — 0.7.
On SWE-Bench, both models are nearly equal: Claude Opus 4.6 — 0.8, Claude Sonnet 4.6 — 0.8.
Claude Sonnet 4.6 is 1.7x cheaper: input $3.00/1M vs $5.00/1M tokens.
Claude Opus 4.6 supports a larger context: 1M vs 200K tokens.
Both models were released around the same time: 2/4/2026 and 2/17/2026.
More About These Models
Related Comparisons
The Claude Opus 4.6 and Claude Sonnet 4.6 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Claude Opus 4.6 or Claude Sonnet 4.6 page. See also the complete list of AI model comparisons.