gpt-oss-120b vs Grok 4.1 Fast
Head to head on 20 shared benchmarks, with price, context window, and release dates.
Benchmark scores
43evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Grok 4.1 Fast xAI | 34.3% | 66.0% | 1324elo | 40.1 | 63.7% | 5.1% | 36.5% | 64.7% | 69.6% | 52.2% | 28.2% | 74.3% | 83.7% | 80.2% | 39.9% | 74.3% | 29.6% | 73.1% | 14.4% | 63.7% | 62.0% | - | - | - | - | 11.8 | - | 35.0% | 80.2% | - | - | 60.8% | 28.1% | 100.0% | 78.7% | - | 42.6% | 4.0% | 31.3% | - | - | - | 1.2% | 51.0% |
| gpt-oss-120b OpenAI | 66.7% | 58.2% | 959elo | 35.8 | 67.2% | 5.9% | 58.3% | 51.0% | 60.2% | 38.8% | 50.3% | 48.6% | 68.9% | 39.2% | 70.7% | 77.5% | 36.0% | 71.6% | 5.3% | 45.0% | - | 41.8% | 38.9% | 7.6% | 13.0% | - | 57.6 | - | - | 1.62 | 1.53 | - | - | - | - | 80.0% | - | - | - | 97.9% | 26.0% | 65.6% | - | 49.6% |
2 / 2 models
| Attribute | gpt-oss-120b OpenAI | Grok 4.1 Fast xAI |
|---|---|---|
| Description | GPT-Oss 120b is an AI model from OpenAI, released with open weights. | Grok 4.1 Fast is an AI model from xAI. |
| Family | GPT | Grok |
| Params | - | - |
| Open weights | open | closed |
| License | apache-2.0 | proprietary |
| Released | 5 Aug 2025 | 19 Nov 2025 |
| Context | 131,072 | - |
| Input $/1M | $0.15 | - |
| Output $/1M | $0.60 | - |
| Cache read $/1M | $0.030 | - |
| Cache write $/1M | - | - |
| Speed | 186 tok/s | 0 tok/s |
| Latency | 0.50 s | 0.00 s |
| Modalities | text | text |
| Providers | - | - |
| Publisher | OpenAI | xAI |
| Reported scores | GPQA Diamond67.2% (AA) Humanity's Last Exam (HLE)5.9% (AA) LiveCodeBench70.7% (AA) MMLU-Pro77.5% (AA) SciCode36.0% (AA) | Infraresolutionbench80.2% (150 samples) Agent Diff Bench62.0% (179 samples) Medpt100.0% (15 samples) Hanabi11.8 (15 samples) SciCode29.6% (AA) |
FAQ
- Is gpt-oss-120b or Grok 4.1 Fast better?
- Across the 20 benchmarks both models report on Sophon, Grok 4.1 Fast leads on 12 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do gpt-oss-120b and Grok 4.1 Fast compare on GPQA Diamond?
- gpt-oss-120b scores 67.2% and Grok 4.1 Fast scores 63.7% on GPQA Diamond.
- When were gpt-oss-120b and Grok 4.1 Fast released?
- gpt-oss-120b was released 5 Aug 2025 by OpenAI. Grok 4.1 Fast was released 19 Nov 2025 by xAI.
Comparing something else? Build your own side-by-side.