RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 2.5 Flash (7/17)

3 benchmarks · 6 observations · 3 sources

Scores at a glance

3 benchmarks · large dot: Gemini 2.5 Flash (7/17); small dots: closest models where reported

MedCode ↗38.42 %
38.4238.42

Gemini 2.5 Flash (7/17) (Nonthinking) · MedCode · Accuracy ↗

1 more reported result

40.36 % · Gemini 2.5 Flash (7/17) (Thinking) · MedCode · Accuracy · Vals AI · MedCode ↗

MedScribe ↗82.87 %
82.8782.87

Gemini 2.5 Flash (7/17) (Nonthinking) · MedScribe · Accuracy ↗

1 more reported result

82.98 % · Gemini 2.5 Flash (7/17) (Thinking) · MedScribe · Accuracy · Vals AI · MedScribe ↗

Closest models by score

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

There are not enough shared scored settings to identify close comparisons reliably.

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. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  2. MedScribe — evaluation methodology and results ↗

    Vals AI · 2026

  3. SAGE — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Gemini 2.5 Flash (7/17) (Nonthinking) · Gemini 2.5 Flash (7/17) (Thinking)