RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 2.5 Pro Preview 03-25

2 benchmarks · 2 observations · 2 sources

Scores at a glance

2 benchmarks · large dot: Gemini 2.5 Pro Preview 03-25; small dots: closest models where reported

ForecastBench ↗64.4 Brier index
46.467

gemini-2.5-pro-preview-03-25† · Overall difficulty-adjusted Brier index ↗

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. Aider code editing benchmark ↗

    Paul Gauthier, Aider contributors

  2. Forecastbench — methodology and published results ↗

    Epoch AI · 2026

Names used in source tables

Gemini 2.5 Pro Preview 03-25 · gemini-2.5-pro-preview-03-25†