GPT-4.1 Mini vs gpt-oss-120b
Head to head on 15 shared benchmarks, with price, context window, and release dates.
Benchmark scores
155evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-4.1 Mini OpenAI | 32.4% | 46.3% | 57.9% | 1144elo | 66.4% | 5.0% | 38.3% | 48.3% | 0.35 | 78.1% | 40.4% | 23.9% | 71.9% | 7.6% | 52.9% | -0.17 | 60.0% | 100.0% | 0.0% | 3 | 43.0% | 98.2% | 0.0% | 28.2% | -1 | 1.07 | 62.3% | 89.9% | - | - | 100 | 83.62 | 0.79 | 0.0% | -0.04 | 0.0% | 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% | 9.0% | 80.0% | 80.0% | 83.4% | 48.6% | - | 43.3% | 100.0% | 58.2% | 52.9% | 0.0% | 4.5% | 1.5% | 18.7% | 50.0% | 65.0% | 56.8% | 0.0% | 100.0% | 3.47 | 3.47 | 1.55 | - | 100.0% | 63.3% | 0.0% | 0.0% | 67.5% | 40.2% | 83.5% | 6.7% | 62.4% | 43.8% | 26.7% | - | - | - | - | - | - | - | 45.4% | 80.0% | - | 100.0% | 93.3% | 100.0% | 92.5% | 2.61 | 0.0% | 100.0% | 77.9% | 5 | 0.0% | - | 64.0% | 64.0% | 20.0% | 26.7% | 54.5% | 65.5% | 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% | 1.04 | 100.0% | 100.0% | 45.6% | 93.3% | 100.0% | 29.0% | 90.0% | 29.0% | 82.0% | 82.0% | 50.8% |
| gpt-oss-120b OpenAI | 41.8% | 66.7% | 58.2% | 959elo | 67.2% | 5.9% | 58.3% | 70.7% | 1.62 | 77.5% | 36.0% | 26.0% | 71.6% | 5.3% | 45.0% | - | - | - | - | - | - | - | - | - | - | - | - | - | 38.9% | 7.6% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 13.0% | - | - | - | - | - | - | - | 35.8 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 57.6 | - | - | - | - | - | - | - | - | - | - | - | 51.0% | 60.2% | 38.8% | 50.3% | 48.6% | 68.9% | 39.2% | - | - | 1.53 | - | - | - | - | - | - | - | - | - | - | 80.0% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 97.9% | - | - | - | - | - | 65.6% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 49.6% |
2 / 2 models
| Attribute | GPT-4.1 Mini OpenAI | gpt-oss-120b OpenAI |
|---|---|---|
| Description | GPT-4.1 Mini is an AI model from OpenAI. | GPT-Oss 120b is an AI model from OpenAI, released with open weights. |
| Family | GPT | GPT |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | apache-2.0 |
| Released | 14 Apr 2025 | 5 Aug 2025 |
| Context | 1,047,576 | 131,072 |
| Input $/1M | $0.40 | $0.15 |
| Output $/1M | $1.60 | $0.60 |
| Cache read $/1M | $0.100 | $0.030 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 186 tok/s |
| Latency | 0.00 s | 0.50 s |
| Modalities | image, text, file | text |
| Providers | - | - |
| Publisher | OpenAI | OpenAI |
| Reported scores | GPQA Diamond67.2% (AA) Humanity's Last Exam (HLE)5.9% (AA) LiveCodeBench70.7% (AA) MMLU-Pro77.5% (AA) SciCode36.0% (AA) |
FAQ
- Is GPT-4.1 Mini or gpt-oss-120b better?
- Across the 15 benchmarks both models report on Sophon, gpt-oss-120b leads on 9 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-oss-120b compare on GPQA Diamond?
- GPT-4.1 Mini scores 66.4% and gpt-oss-120b scores 67.2% on GPQA Diamond.
- Which is cheaper, GPT-4.1 Mini or gpt-oss-120b?
- gpt-oss-120b is cheaper at $0.60 per million output tokens against $1.60 for GPT-4.1 Mini - about 2.7x.
- When were GPT-4.1 Mini and gpt-oss-120b released?
- GPT-4.1 Mini was released 14 Apr 2025 by OpenAI. gpt-oss-120b was released 5 Aug 2025 by OpenAI.
Comparing something else? Build your own side-by-side.