Vision-language

Gemini 2.0 Pro

By Google DeepMind, in the Gemini Pro family.

Released
6 Dec 2024
Status
Retired
Retired
9 Dec 2025
Context
2.1M
Max output
8.2K
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
Aug 2024
Reasoning
No
Modalities
text, image, audio, video → text

Category scores

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

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning17.3Not ranked1 of 4
Coding & software engineering38.2Not 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
SimpleBenchScore (AVG@5)31.1%Third party——SimpleBench Leaderboard via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy65.7%Independent—7 Feb 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
MATH Level 5Accuracy83.5%Independent—6 Feb 2025Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Aider PolyglotPercent correct38.2%Third party——https://aider.chat/docs/leaderboards/ via Epoch AI
Aider PolyglotPercent correct35.6%Third party——https://aider.chat/docs/leaderboards/ via Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)41.7%Third party——Fiction.live leaderboard via Epoch AI

Other Gemini Pro versions

Sources