Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

StartLuxLabs/DecisionPivot

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.

Owner
StartLuxLabs (organization)
Stars
Stars: 152
Forks
Forks: 3
Language
Python
License
Apache-2.0
Created
2026
Topics
benchmarkcalibrationdecision-makingevaluationllmllm-evaluationselective-prediction
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by StartLuxLabs

All 3 repos by StartLuxLabs

Nearby in Python

All Python repos