RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 2.0 Flash (Feb 2025)

14 benchmarks · 14 observations · 14 sources · released 2025-02-05

Scores at a glance

14 benchmarks · large dot: Gemini 2.0 Flash (Feb 2025); small dots: closest models where reported

GPQA Diamond ↗64.14%
9.2896.4

Gemini 2.0 Flash (Feb 2025) · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗82.17%
3.2998.13

Gemini 2.0 Flash (Feb 2025) · MATH level 5 · Best score (across scorers) · % ↗

CadEval ↗30%
1274

Gemini 2.0 Flash (Feb 2025) · CadEval · Overall pass (%) · % ↗

GeoBench ↗77%
3286

Gemini 2.0 Flash (Feb 2025) · GeoBench · ACW Country % · % ↗

DTBench ↗63.2%
41.6598.93

Gemini 2.0 Flash (Feb 2025) · DTBench · Accuracy · % ↗

LiveBench ↗61.47%
22.0882.35

Gemini 2.0 Flash (Feb 2025) · LiveBench · Global average · % ↗

EnigmaEval ↗0.63%
0.3839.28

Gemini 2.0 Flash (Feb 2025) · EnigmaEval · Accuracy · % ↗

Closest models by score

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

4.0 percentile-point gap

3 of 4 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. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  2. ARC-AGI-2 ↗

    Epoch AI

  3. FrontierMath Tiers 1-3 (v1, old) ↗

    Epoch AI

  4. GPQA Diamond ↗

    Epoch AI

  5. MATH Level 5 ↗

    Epoch AI

  6. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  7. The Agent Company ↗

    Epoch AI

  8. AI benchmarks & capabilities ↗

    Epoch AI

  9. Fiction.liveBench — March 14, 2025 benchmark release ↗

    Fiction.live · 2025

  10. GeoBench — GeoGuessr model benchmark ↗

    GeoBench

  11. WeirdML ↗

    Håvard Tveit Ihle

  12. EnigmaEval ↗

    Scale Labs / SEAL

  13. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

  14. CadEval Dashboard — run 20250422_095709 ↗

    willpatrick · 2025

Names used in source tables

Gemini 2.0 Flash (Feb 2025)