supermarket

Vision-language

Gemma 2 27B

By Google DeepMind, in the Gemma family.

Released
27 Jun 2024
Status
Legacy
Context
8.2K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
gemma
Parameters
27.23B
Knowledge cutoff
—
Reasoning
No
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning8.4Not ranked1 of 4
Human preference34.6Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DTBench (Decision Theory Benchmark)Accuracy (capability questions)48.0%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.071Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLUAccuracy75.7%Third party——Stanford CRFM Leaderboard via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy36.5%Independent—27 Jan 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
MATH Level 5Accuracy27.9%Independent—27 Jan 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy1.4%Independent—7 Mar 2025Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1289Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes75754Independent—25 Sep 2026Arena

Other Gemma versions

Sources