Claude 4 Sonnet vs GPT-4.1
Head to head on 19 shared benchmarks, with price, context window, and release dates.
Benchmark scores
59evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude 4 Sonnet Anthropic | 40.7% | 38.0% | 54.7% | 19.8% | 1480elo | 67.5% | 68.3% | 4.3% | 45.4% | 44.9% | 93.4% | 83.7% | 62.5% | 37.3% | 35.6% | 74.6% | 69.6% | 27.3% | 52.3% | - | - | - | - | - | 22.9% | 47.8% | - | - | 58.4 | - | 64.8% | 77.5% | 54.6% | 44.3% | 72.9% | 70.5% | 69.0% | - | - | - | - | - | 33.9% | - | 72.4% | 86.7% | - | 43.9% | 6.18 | 6.18 | 35.0% | - | 58.3% | - | 0.59 | 84.0% | 84.0% | - | - | 55.5% |
| GPT-4.1 OpenAI | 43.7% | 34.7% | 63.1% | 12.4% | 1417elo | 60.9% | 66.6% | 4.2% | 43.0% | 45.7% | 91.3% | 80.6% | 65.9% | 38.1% | 31.1% | 39.6% | 75.1% | 13.6% | 47.1% | 0.0% | 52.4% | 26.7% | 61.5% | 1.64 | - | - | 83.7% | 1.55 | - | 5.5% | - | - | - | - | - | - | - | 70.8% | 0.49 | 0.49 | 32.1% | 32.1% | - | 69.4% | - | - | 50.5% | - | - | - | - | 8.57 | - | 10.0% | - | - | - | 92.0% | 92.0% | 48.0% |
2 / 2 models
| Attribute | Claude 4 Sonnet Anthropic | GPT-4.1 OpenAI |
|---|---|---|
| Description | Claude 4 Sonnet is an AI model from Anthropic. | GPT-4.1 is an AI model from OpenAI. |
| Family | Claude | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 22 May 2025 | 14 Apr 2025 |
| Context | 200,000 | 1,047,576 |
| Input $/1M | $3.00 | $2.00 |
| Output $/1M | $15.00 | $8.00 |
| 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 | image, text, file |
| Providers | - | - |
| Publisher | Anthropic | OpenAI |
| Reported scores | ScholarSearch8.57 Social Sciences & Humanities (%) GPQA Diamond66.6% (AA) Humanity's Last Exam (HLE)4.2% (AA) IFBench43.0% (AA) |
FAQ
- Is Claude 4 Sonnet or GPT-4.1 better?
- Across the 19 benchmarks both models report on Sophon, Claude 4 Sonnet leads on 13 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do Claude 4 Sonnet and GPT-4.1 compare on GPQA Diamond?
- Claude 4 Sonnet scores 68.3% and GPT-4.1 scores 66.6% on GPQA Diamond.
- Which is cheaper, Claude 4 Sonnet or GPT-4.1?
- GPT-4.1 is cheaper at $8.00 per million output tokens against $15.00 for Claude 4 Sonnet - about 1.9x.
- When were Claude 4 Sonnet and GPT-4.1 released?
- Claude 4 Sonnet was released 22 May 2025 by Anthropic. GPT-4.1 was released 14 Apr 2025 by OpenAI.
Comparing something else? Build your own side-by-side.