Vision-language

Gemini 1.0 Pro

By Google DeepMind, in the Gemini Pro family.

Released
6 Dec 2023
Status
Retired
Retired
21 Apr 2025
Context
30.7K
Max output
2K
Input per 1M tokens
$0.50
Output per 1M tokens
$1.50
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
Nov 2023
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 preference26.6Not 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)45.9%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
MMLUAccuracy70.0%Third party——Stanford CRFM Leaderboard via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy34.0%Independent—27 Jan 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
MATH Level 5Accuracy11.2%Independent—27 Jan 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy1.1%Independent—25 Feb 2025Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1224Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes6390Independent—25 Sep 2026Arena

Other Gemini Pro versions

Sources

Gemini 1.0 Pro: benchmarks, price and specs · supermarket.dev