RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemma2

1 benchmarks · 1 observations · 1 sources

Scores at a glance

1 benchmarks · large dot: Gemma2; small dots: closest models where reported

MedAgentBench ↗19.33%
469.67

Gemma2 · MedAgentBench · Overall task success · original evaluation ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

18.2 percentile-point gap

1 of 1 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents — published result table ↗

    Jiang, Yixing, Black, Kameron C., Geng, Gloria, Park, Danny, Zou, James, Ng, Andrew Y. et al. · 2025

    All 7 authors

    Jiang, Yixing, Black, Kameron C., Geng, Gloria, Park, Danny, Zou, James, Ng, Andrew Y., Chen, Jonathan H.

Names used in source tables

Gemma2