CategoryReasoning
MeasureAudited progress level 0 to 4 per task, refined to a fractional score; complete-run mean across all tasks
Tasks120 research tasks, 20 in each of six STEM domains
DifficultyOpen research targets; no run has reached a full-target success
Scores how far a model advances 120 open research tasks across biology, chemistry, physics, astronomy, Earth science and engineering on a 0 to 4 progress scale, crediting supported partial work and honest statements of what remains unresolved.
About STEMBench
What the benchmark measures and how its value is published, from the source’s own record.
What is STEMBench?
STEMBench (STEMBench120: six-domain scientific research progress) is a reasoning benchmark published by STEMBench: six-domain model evaluation. Scores how far a model advances 120 open research tasks across biology, chemistry, physics, astronomy, Earth science and engineering on a 0 to 4 progress scale, crediting supported partial work and honest statements of what remains unresolved. Its evaluation set is described by the source as 120 research tasks, 20 in each of six STEM domains. The source rates its difficulty as open research targets; no run has reached a full-target success.
How is STEMBench scored?
Each model's result is published by STEMBench: six-domain model evaluation as audited progress level 0 to 4 per task, refined to a fractional score; complete-run mean across all tasks. ModelScale prints that value to 2 decimal places, exactly as published, and never converts or rescales it. This page ranks the 9 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale
