TeichAI / gpt-oss family
gpt-oss-20b-high
openai/gpt-oss-20b-high
Benchmarks
Where it scores.
General Provisional
84.7
Coding Provisional
86.5
Math Provisional
87.6
Reasoning Provisional
86.5
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
No recommended variants are indexed for this model.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | AIME2025 | 98.7 | 98.7 |
| ZeroEval | GPQA | 74.2 | 74.2 |
From the Hugging Face model card
About this model.
From the Hugging Face model card