RLTasksby ulam.ai
Models / Google

Google / MODEL EVIDENCE

Gemma 2 27B

10 benchmarks · 10 observations · 10 sources · released 2024-06-24

Scores at a glance

10 benchmarks · large dot: Gemma 2 27B; small dots: closest models where reported

GPQA Diamond ↗36.49%
9.2896.4

Gemma 2 27B · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗27.89%
3.2998.13

Gemma 2 27B · MATH level 5 · Best score (across scorers) · % ↗

MMLU ↗75.7%
29.587.3

Gemma 2 27B · MMLU · EM · % ↗

LMCA ↗7.1%
2.7868.26

Gemma 2 27B · LMCA · Score · % ↗

LiveBench ↗38.18%
22.0882.35

Gemma 2 27B · LiveBench · Global average · % ↗

ZebraLogic ↗16.3%
6.481

Gemma-2-27B · ZebraLogic · Grid-level accuracy · complete puzzles ↗

Closest models by score

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

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. ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning — published result table ↗

    Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark et al. · 2025

    All 7 authors

    Bill Yuchen Lin, Ronan Le Bras, Kyle Richardson, Ashish Sabharwal, Radha Poovendran, Peter Clark, Yejin Choi

  2. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  3. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  4. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  5. GPQA Diamond ↗

    Epoch AI

  6. MATH Level 5 ↗

    Epoch AI

  7. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  8. AI benchmarks & capabilities ↗

    Epoch AI

  9. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

  10. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Gemma 2 (27B) · Gemma 2 27B · Gemma-2-27B