What it measures
Research-level physics challenges are attempted with code execution in an offline Linux sandbox.
How to read the result
Useful for studying the interaction of physical reasoning, calculation, and computational checking.
Limits and comparison traps
This revised version changes tasks and tool conditions. Keep it separate from the original CritPt score.
Benchmark reference notes
70 composite research-level physics challenges solved with code execution in an offline Linux sandbox.
Where this fits in an evaluation suite
A correct multiple-choice answer and a supported scientific contribution demand different evidence. Check whether the score rewards a proposal, an executed experiment, or a completed research target.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Use the exact implementation, version, task subset, tool access, attempt budget, and judge described by the source.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.