gpt-oss-120b
#118 of 274 scored.
OpenAIAug 5, 2025Open weights
Capabilities Index
Range 135.2–142.8
139.9
Context
Takes text
131K
Input
Per 1M tokens
$0.037
Output
Per 1M tokens
$0.17
Benchmarks
How it scores.
- GPQA Diamond67.7%
92nd of 186
- Mock AIME88.9%
54th of 176
- Terminal-Bench18.7%
31st of 35
Everything else Epoch has for it
- Lech Mazur Writing77.1%
- DTBench60.5%
- METR Time Horizons56.6%
- WeirdML48.2%
- Fiction.LiveBench44.4%
- Aider polyglot41.8%
- LMCA26.1%
- Surface Evolver Bench25.0%
- Chess Puzzles15.8%
- SimpleBench6.5%
- APEX-Agents4.4%
- Mystery Game Puzzles0.0%
On the index
Around it.
Sources