supermarket

Vision-language

Gemma 2 9B

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
9.24B
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
Human preference31.7Not 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
MMLUAccuracy72.1%Third party——Stanford CRFM Leaderboard via Epoch AI
PIQAAccuracy83.7%Self-reported——Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy27.5%Independent—27 Jan 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GSM8KExact match84.9%Self-reported——Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone via Epoch AI
MATH Level 5Accuracy21.0%Independent—27 Jan 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy0.6%Independent—7 Mar 2025Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1267Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes54611Independent—25 Sep 2026Arena

Other Gemma versions

Sources