specific method · not yet filed
Inference-time scaling plots for evaluation reporting
Also called Inference-time scaling plots.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Added plots for both bio and cyber evals showing how performance scales with number of trials.
usedevaluation onlyin gpt-oss-120b and gpt-oss-20bOpenAI