Gemini 2.5 Pro Experimental 03-25 Benchmark Details

Gemini 2.5 Pro Experimental 03-25 currently shows benchmark results led by AIME 2024 (9 / 61, score 92), Aider-Polyglot (12 / 59, score 72.90), GeoBench ACW (5 / 20, score 81).

Benchmark Results

Gemini 2.5 Pro Experimental 03-25

Benchmark Results

Knowledge Exams

2 evaluations

Benchmark / mode

Score

Rank/total

HLE

Standard Mode

18.80

162 / 233

HLE

unknown

18.16

165 / 233

Scientific Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

97 / 253

Honesty & Factuality

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleQA

Standard Mode

52.90

13 / 46

Repository Engineering

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Standard Mode

63.80

78 / 116

Mathematics

3 evaluations

Benchmark / mode

Score

Rank/total

AIME 2024

Standard Mode

9 / 61

AIME2025

Standard Mode

86.90

52 / 110

FrontierMath - Tier 4

Standard Mode

4.20

40 / 80

Algorithmic Coding

1 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Standard Mode

70.40

57 / 125

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1393.40

65 / 106

Commonsense

1 evaluations

Benchmark / mode

Score

Rank/total

SimpleBench

Standard Mode

51.60

52 / 96

Agentic Development

1 evaluations

Benchmark / mode

Score

Rank/total

Aider-Polyglot

Standard Mode

72.90

12 / 59

Tool Orchestration

2 evaluations

Benchmark / mode

Score

Rank/total

Claw Bench

Thinking EnabledTools

80.40

20 / 29

Pinch Bench

Thinking EnabledTools

71.90

30 / 38

Visual Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

GeoBench ACW

Standard ModeToolsInternet

5 / 20

VPCT

Standard Mode

11 / 24

Long Reasoning

1 evaluations

Benchmark / mode

Score

Rank/total

Fiction.liveBench

Standard Mode

66.70

13 / 16

Logical Planning

1 evaluations

Benchmark / mode

Score

Rank/total

BALROG

Standard ModeTools

43.30

6 / 12

Compare with other models