GPT-4.1 Mini vs GPT-5
Head to head on 41 shared benchmarks, with price, context window, and release dates.
Benchmark scores
160evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 46.7% | 91.1% | 88.0% | 94.6% | 48.3% | 0.0% | 0.15 | 0.0% | 61.1% | 57.7% | 80.0% | 80.0% | 1623elo | 91.7% | 32.4% | 88.9% | 68.6% | 100.0% | 6.6% | 48.9% | 45.0% | 58.2% | 54.3% | 0.52 | 100.0% | 86.1% | 0.0% | 10.0% | 82.0% | 0.0% | 65.5% | 60.0% | 37.8% | 74.4% | 73.4% | 12.9% | 0.86 | 54.8% | 90.0% | 90.0% | 0.0% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 68.1% | 4.58 | - | - | - | - | - | - | - | - | - | - | - | - | - | 72.8 | - | - | - | - | - | - | 0.0% | 83.3% | - | - | - | - | - | - | - | - | - | - | - | - | 83.4% | - | - | - | 37.5% | - | - | 1.62 | - | - | - | - | 92.7% | 92.7% | 49.6% | - | 83.7% | - | 93.3% | - | - | - | - | 0.26 | - | - | - | - | - | - | - | 0.0% | 18.0% | - | - | - | - | - | 43.7% | - | - | - | - | - | - | - | - | - | - | - | - | 74.9% | - | - | 2.34 | - | - | - | 87.5% | - | - | - | - | - | 20.1% | - | - | 56.7% |
| GPT-4.1 Mini OpenAI | 60.0% | 0.0% | 32.4% | 43.0% | 46.3% | 0.0% | 0.79 | 0.0% | 57.9% | 9.0% | 80.0% | 80.0% | 1144elo | 58.2% | 4.5% | 50.0% | 66.4% | 100.0% | 5.0% | 40.2% | 38.3% | 62.4% | 48.3% | 0.35 | 100.0% | 92.5% | 0.0% | 26.7% | 78.1% | 54.5% | 65.5% | 20.0% | 40.4% | 23.9% | 71.9% | 7.6% | 1.04 | 29.0% | 82.0% | 82.0% | 52.9% | -0.17 | 100.0% | 3 | 98.2% | 28.2% | -1 | 1.07 | 62.3% | 89.9% | 100 | 83.62 | 0.0% | -0.04 | 0.0% | 1.11 | 1.11 | - | - | 1.01 | 204.5 | 40.0% | 41.7% | 1.45 | 34.5% | 13.0% | 53.6% | 3.6% | 17.4% | 3.3% | 83.4% | 48.6% | - | 43.3% | 100.0% | 52.9% | 0.0% | 1.5% | 18.7% | - | - | 65.0% | 56.8% | 0.0% | 3.47 | 3.47 | 1.55 | 100.0% | 63.3% | 0.0% | 0.0% | 67.5% | 83.5% | - | 6.7% | 43.8% | 26.7% | - | 45.4% | 80.0% | - | 93.3% | 100.0% | 2.61 | 100.0% | - | - | - | 77.9% | - | 5 | - | 0.0% | 64.0% | 64.0% | 20.0% | - | 20.0% | 30.0% | 19.5% | 96.5% | 52.0% | 30.0% | 30.0% | - | - | 60.0% | 0.0% | 46.8% | 93.0% | 40.6% | - | 100.0% | 88.2% | 100.0% | 20.0% | 33.3% | 100.0% | 73.3% | 100.0% | 1.14 | 56.72 | 0 | 10.0% | - | 100.0% | 100.0% | - | 0.0% | 100.0% | 37.6% | - | 100.0% | 100.0% | 45.6% | 93.3% | 100.0% | - | 90.0% | 29.0% | 50.8% |
2 / 2 models
| Attribute | GPT-4.1 Mini OpenAI | GPT-5 OpenAI |
|---|---|---|
| Description | GPT-4.1 Mini is an AI model from OpenAI. | OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant. |
| Family | GPT | GPT 5 |
| Params | - | Undisclosed (closed) |
| Open weights | closed | closed |
| License | proprietary | Proprietary |
| Released | 14 Apr 2025 | 7 Aug 2025 |
| Context | 1,047,576 | 400,000 |
| Input $/1M | $0.40 | - |
| Output $/1M | $1.60 | - |
| Cache read $/1M | $0.100 | $0.125 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | image, text, file | text, image, file |
| Providers | - | openai |
| Publisher | OpenAI | OpenAI |
| Reported scores |
FAQ
- Is GPT-4.1 Mini or GPT-5 better?
- Across the 41 benchmarks both models report on Sophon, GPT-5 leads on 24 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-4.1 Mini and GPT-5 compare on GPQA Diamond?
- GPT-4.1 Mini scores 66.4% and GPT-5 scores 68.6% on GPQA Diamond.
- When were GPT-4.1 Mini and GPT-5 released?
- GPT-4.1 Mini was released 14 Apr 2025 by OpenAI. GPT-5 was released 7 Aug 2025 by OpenAI.
Comparing something else? Build your own side-by-side.