Google / MODEL EVIDENCE

Gemini 2.0 Flash (Dec 2024)

6 benchmarks · 9 observations · 6 sources

Scores at a glance

6 benchmarks · large dot: Gemini 2.0 Flash (Dec 2024); small dots: closest models where reported

29.587.3

Gemini 2.0 Flash (Dec 2024) · MMLU · EM · % ↗

64.0964.09

Gemini 2.0 Flash (Dec 2024) · LiveBench · Global average · % ↗

1 more reported result

59.26% · Gemini 2.0 Flash (Dec 2024) · LiveBench · Global average · % · Epoch AI · LiveBench ↗

Closest models by score

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

13.1 percentile-point gap

2 of 2 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.

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 LLM Leaderboards — Polyglot coding benchmark ↗

    Aider

  2. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  3. SimpleBench ↗

    Epoch AI

  4. AI benchmarks & capabilities ↗

    Epoch AI

  5. Writing benchmark — incorporating mandatory story elements ↗

    lechmazur

  6. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

Release dates reported by sources

2024-12-06 · 2024-12-11

Names used in source tables

Gemini 2.0 Flash (Dec 2024)