OpenProblemBench tests AI on 82 still-unsolved science problems
OpenProblemBench gives AI systems 82 unresolved questions from mathematics and theoretical physics, shifting evaluation from known-answer tests toward research problems with no reference solutions. Each task includes its context, assumptions, and prior progress, while four evaluator models judge correctness, completeness, and progress. In seven configurations, GPT-6-Astra reached a 14.0% mean judged solve rate, versus 5.5% to 6.7% for full-size open models and 2.4% to 3.7% for Flash models.