GPT-4.1 vs GPT-5.2
Head to head on 15 shared benchmarks, with price, context window, and release dates.
Benchmark scores
66evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.2 OpenAI | 51.0% | 65.9% | 1699elo | 40.7% | 71.2% | 8.0% | 47.4% | 66.9% | 81.4% | 67.1% | 40.4% | 71.8% | 75.8% | 31.8% | 46.5% | - | - | - | 100 | - | - | - | 100.0% | 0.0% | 16.7% | - | - | 60.0% | 40.6% | 9.4% | - | 71.6 | - | 12.93 | 85.0% | 79.0% | 78.7% | 76.1% | 78.2% | 61.8% | 79.8% | 93.2% | 83.2% | 24.0% | - | - | - | - | 72.0% | - | - | 49.7% | - | 84.4% | - | 96.7 | 18.7% | 15.0% | 49.3% | - | 66.7% | - | - | 53.5% | - | - | 56.3% |
| GPT-4.1 OpenAI | 34.7% | 63.1% | 1417elo | 5.5% | 66.6% | 4.2% | 43.0% | 45.7% | 80.6% | 65.9% | 38.1% | 39.6% | 75.1% | 13.6% | 47.1% | 0.0% | 52.4% | 43.7% | - | 26.7% | 61.5% | 1.64 | - | - | - | 83.7% | 1.55 | - | - | - | 12.4% | - | 60.9% | - | - | - | - | - | - | - | - | - | - | - | 70.8% | 0.49 | 0.49 | 91.3% | - | 32.1% | 32.1% | - | 69.4% | - | 50.5% | - | - | - | - | 8.57 | - | 31.1% | 10.0% | - | 92.0% | 92.0% | 48.0% |
2 / 2 models
| Attribute | GPT-4.1 OpenAI | GPT-5.2 OpenAI |
|---|---|---|
| Description | GPT-4.1 is an AI model from OpenAI. | GPT-5.2 is an AI model from OpenAI. |
| Family | GPT | GPT |
| Params | - | - |
| Open weights | closed | closed |
| License | proprietary | proprietary |
| Released | 14 Apr 2025 | 11 Dec 2025 |
| Context | 1,047,576 | 400,000 |
| Input $/1M | $2.00 | $1.75 |
| Output $/1M | $8.00 | $14.00 |
| Cache read $/1M | $0.500 | $0.175 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | image, text, file | file, image, text |
| Providers | - | - |
| Publisher | OpenAI | 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 GPT-4.1 or GPT-5.2 better?
- Across the 15 benchmarks both models report on Sophon, GPT-5.2 leads on 14 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4.1 and GPT-5.2 compare on GPQA Diamond?
- GPT-4.1 scores 66.6% and GPT-5.2 scores 71.2% on GPQA Diamond.
- Which is cheaper, GPT-4.1 or GPT-5.2?
- GPT-4.1 is cheaper at $8.00 per million output tokens against $14.00 for GPT-5.2 - about 1.8x.
- When were GPT-4.1 and GPT-5.2 released?
- GPT-4.1 was released 14 Apr 2025 by OpenAI. GPT-5.2 was released 11 Dec 2025 by OpenAI.
Comparing something else? Build your own side-by-side.