ambiguous · filed under evaluation
Benchmark evaluation framework
A benchmark framework for evaluating trained models; the evidence does not identify a more specific framework.
Also called benchmark framework.
- 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.
Tinker Cookbook includes a benchmark framework for evaluating trained models
usedevaluation onlyin tinker-cookbookThinking Machines Lab
Filed alongside
Other methods under evaluation :: evaluation harness.
DeepSeek Harness Minimal modeHarborNeMo Evaluator SDKAtomic binary rubric evaluationAutomatic in-flight checkpoint evaluation schedulingCross-scaffold evaluationInline training evaluatorsIsolated container per rolloutJSON-structured answer-format promptmini-swe-agent harnessNeMo Gym and NeMo Evaluator-based harnessNeMo SkillsPool