Claude 4 Sonnet vs GPT-5.5
Head to head on 23 shared benchmarks, with price, context window, and release dates.
Benchmark scores
69evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.5 OpenAI | 68.4% | 1844elo | 78.2 | 76.8% | 13.7% | 46.1% | 84.7% | 82.5% | 81.1% | 73.0% | 87.7% | 96.3% | 87.7% | 49.1% | 86.9% | 88.6% | 68.8% | 78.7% | 51.5% | 47.3% | 75.0% | 49.2% | 69.3% | - | - | 86.2% | 54.2% | 12.9% | - | 36.2% | - | 86.0% | 90.0% | 100.0% | - | 1315elo | 34.0% | 51.8% | 5.7% | 51.7% | 44.8% | 24.9% | 1769elo | - | 15.1% | 51.8% | 2.1% | - | - | 92.8% | - | 45.3% | 100.0% | 50.0% | - | - | 4.2 | - | - | - | 58.6% | 75.7% | 83.4% | - | 57.4% | 68.1% | 69.8% | - | - | 61.9% |
| 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% | 83.7% | 62.5% | 43.9% | 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% | - | - | - | 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 | GPT-5.5 OpenAI |
|---|---|---|
| Description | Claude 4 Sonnet is an AI model from Anthropic. | GPT-5.5 is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 22 May 2025 | 23 Apr 2026 |
| Context | 200,000 | 1,050,000 |
| Input $/1M | $3.00 | $5.00 |
| Output $/1M | $15.00 | $30.00 |
| Cache read $/1M | - | $0.500 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text, image | file, image, text |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | GPQA Diamond76.8% (AA) Humanity's Last Exam (HLE)13.7% (AA) IFBench46.1% (AA) SciCode47.3% (AA) τ²-bench (Tau²-bench)69.3% (AA) |
FAQ
- Is Claude 4 Sonnet or GPT-5.5 better?
- Across the 23 benchmarks both models report on Sophon, GPT-5.5 leads on 23 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 4 Sonnet and GPT-5.5 compare on GPQA Diamond?
- Claude 4 Sonnet scores 68.3% and GPT-5.5 scores 76.8% on GPQA Diamond.
- Which is cheaper, Claude 4 Sonnet or GPT-5.5?
- Claude 4 Sonnet is cheaper at $15.00 per million output tokens against $30.00 for GPT-5.5 - about 2.0x.
- When were Claude 4 Sonnet and GPT-5.5 released?
- Claude 4 Sonnet was released 22 May 2025 by Anthropic. GPT-5.5 was released 23 Apr 2026 by OpenAI.
Comparing something else? Build your own side-by-side.