šŸŒ US-Proxy
>

GAMOW LABS / EVALUATIONS

Benchmarks

AI agents, tested on real scientific problems.
From rare disease diagnosis to the next experiment.

RAREBENCH122cases
LABBENCH20tasks

Independent evals are the best disinfectant

Connecting to resultsā€¦

01 / RARE DISEASE DIAGNOSIS

RareBench

Can an agent identify the causal findings in a rare disease case?

Read the study

Complete causal recall

Loading graded resultsā€¦

All required causal findings within the first K ranked findings; K is the number of required findings for each case.

  1. Loading resultsā€¦

Whiskers show 95% Wilson intervals. Invalid outputs count as failures.

02 / EXPERIMENTAL REASONING

LabBench

Can an agent reason from lab evidence to the right next experiment?

Read the study
MetricMean task score

Mean task score

Loading graded resultsā€¦

The average fraction of rubric criteria passed per task. Each task has equal weight.

  1. Loading resultsā€¦

Only complete, fully reviewed 20-task configurations are shown.