RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemini 1.5 Pro (Sept 2024)

13 benchmarks · 13 observations · 13 sources · released 2024-09-24

Scores at a glance

13 benchmarks · large dot: Gemini 1.5 Pro (Sept 2024); small dots: closest models where reported

GPQA Diamond ↗57.23%
9.2896.4

Gemini 1.5 Pro (Sept 2024) · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗70.39%
3.2998.13

Gemini 1.5 Pro (Sept 2024) · MATH level 5 · Best score (across scorers) · % ↗

BALROG ↗21%
3.768.3

Gemini 1.5 Pro (Sept 2024) · Balrog · Average progress · % ↗

CadEval ↗34%
1274

Gemini 1.5 Pro (Sept 2024) · CadEval · Overall pass (%) · % ↗

MMLU ↗86.9%
29.587.3

Gemini 1.5 Pro (Sept 2024) · MMLU · EM · % ↗

SimpleBench ↗27.1%
10.781.9

Gemini 1.5 Pro (Sept 2024) · SimpleBench · Score (AVG@5) · % ↗

DTBench ↗58.98%
41.6598.93

Gemini 1.5 Pro (Sept 2024) · DTBench · Accuracy · % ↗

Closest models by score

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

2.6 percentile-point gap

3 of 3 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. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ↗

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir et al. · 2024

    All 13 authors

    Paglieri, Davide, Cupiał, Bartłomiej, Coward, Samuel, Piterbarg, Ulyana, Wolczyk, Maciej, Khan, Akbir, Pignatelli, Eduardo, Kuciński, Łukasz, Pinto, Lerrel, Fergus, Rob, Foerster, Jakob Nicolaus, Parker-Holder, Jack, Rocktäschel, Tim

  2. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  3. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  4. ARC-AGI-2 ↗

    Epoch AI

  5. GPQA Diamond ↗

    Epoch AI

  6. Humanity's Last Exam ↗

    Epoch AI

  7. MATH Level 5 ↗

    Epoch AI

  8. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  9. SimpleBench ↗

    Epoch AI

  10. The Agent Company ↗

    Epoch AI

  11. AI benchmarks & capabilities ↗

    Epoch AI

  12. WeirdML ↗

    Håvard Tveit Ihle

  13. CadEval Dashboard — run 20250422_095709 ↗

    willpatrick · 2025

Names used in source tables

Gemini 1.5 Pro (Sept 2024)