Claude 4 Sonnet vs Claude Opus 4.7
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
54evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.7 Anthropic | 66.1% | 1906elo | 81.8 | 88.5% | 33.3% | 43.6% | 79.7% | 82.1% | 78.3% | 59.3% | 77.9% | 93.1% | 87.7% | 54.9% | 83.0% | 70.3% | 56.1% | 50.1% | 75.3% | 54.5% | 74.0% | - | - | 3.21 | - | - | 79.0% | - | 1311elo | 51.5% | 43.8% | - | - | - | 73.2% | - | - | 91.5 | - | 45.3% | 100.0% | 54.0% | - | - | - | - | - | 72.8 | - | 56.1% | 67.4% | 71.0% | - | - | 67.2% |
| Claude 4 Sonnet Anthropic | 54.7% | 1480elo | 58.4 | 68.3% | 4.3% | 45.4% | 64.8% | 77.5% | 54.6% | 44.3% | 72.9% | 70.5% | 69.0% | 33.9% | 72.4% | 62.5% | 35.0% | 37.3% | 69.6% | 27.3% | 52.3% | 40.7% | 38.0% | - | 22.9% | 47.8% | - | 19.8% | - | - | - | 67.5% | 44.9% | 93.4% | - | 86.7% | 83.7% | - | 43.9% | - | - | - | 6.18 | 6.18 | 58.3% | 35.6% | 74.6% | - | 0.59 | - | - | - | 84.0% | 84.0% | 55.5% |
2 / 2 models
| Attribute | Claude 4 Sonnet Anthropic | Claude Opus 4.7 Anthropic |
|---|---|---|
| Description | Claude 4 Sonnet is an AI model from Anthropic. | Claude Opus 4.7 is an AI model from Anthropic. |
| Family | Claude | Claude |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 22 May 2025 | 16 Apr 2026 |
| Context | 200,000 | 1,000,000 |
| Input $/1M | $3.00 | $5.00 |
| Output $/1M | $15.00 | $25.00 |
| Cache read $/1M | - | $0.500 |
| Cache write $/1M | - | $6.250 |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image | text, image, file |
| Providers | - | - |
| Publisher | Anthropic | Anthropic |
| Reported scores | GPQA Diamond88.5% (AA) Humanity's Last Exam (HLE)33.3% (AA) IFBench43.6% (AA) τ²-bench (Tau²-bench)74.0% (AA) Terminal-Bench (Hard)54.5% (AA) |
FAQ
- Is Claude 4 Sonnet or Claude Opus 4.7 better?
- Across the 21 benchmarks both models report on Sophon, Claude Opus 4.7 leads on 20 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 4 Sonnet and Claude Opus 4.7 compare on GPQA Diamond?
- Claude 4 Sonnet scores 68.3% and Claude Opus 4.7 scores 88.5% on GPQA Diamond.
- Which is cheaper, Claude 4 Sonnet or Claude Opus 4.7?
- Claude 4 Sonnet is cheaper at $15.00 per million output tokens against $25.00 for Claude Opus 4.7 - about 1.7x.
- When were Claude 4 Sonnet and Claude Opus 4.7 released?
- Claude 4 Sonnet was released 22 May 2025 by Anthropic. Claude Opus 4.7 was released 16 Apr 2026 by Anthropic.
Comparing something else? Build your own side-by-side.