Model techniques map
Techniquesevaluationbenchmark

implementation detail · filed under evaluation

High-confidence ProgramBench subset

A ProgramBench subset retaining tasks whose reference solution achieves at least a 95% pass rate on the hidden test suite.

Also called High-confidence benchmark subset filtering, high-confidence subset of ProgramBench.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

We construct a high-confidence subset of ProgramBench by retaining only tasks for which the reference solution achieves a pass rate of at least 95% on the hidden test suite.

useddata curationin DeepSeek-V4.1-FlashDeepSeek

by retaining only tasks for which the reference solution achieves a pass rate of at least 95% on the hidden test suite

usedevaluation onlyin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under evaluation :: benchmark.