DataLearner logo

Gemini-2.5-Pro-Preview-05-06 Benchmark Details

Gemini-2.5-Pro-Preview-05-06 currently shows benchmark results led by MATH-500 (1 / 46, score 98.80), AIME 2024 (9 / 61, score 92), GeoBench ACW (3 / 20, score 86).

Benchmark Results

Gemini-2.5-Pro-Preview-05-06

Benchmark Results

Thinking
Tool usage
Internet

Knowledge Exams

1 evaluations
Benchmark / mode
Score
Rank/total
HLE
Standard Mode
21.60
149 / 235

Scientific Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
83
107 / 253

Honesty & Factuality

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
54
11 / 46

Repository Engineering

1 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Standard Mode
63.20
79 / 116

Mathematics

5 evaluations
Benchmark / mode
Score
Rank/total
MATH-500
Standard Mode
98.80
1 / 46
AIME 2024
Standard Mode
92
9 / 61
AIME2025
Standard Mode
83
59 / 110
FrontierMath
Standard Mode
10.30
25 / 60
FrontierMath - Tier 4
Standard Mode
2.10
56 / 80

Algorithmic Coding

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
77.10
37 / 125

Visual Understanding

4 evaluations
Benchmark / mode
Score
Rank/total
GeoBench ACW
Standard Mode
86
3 / 20
GeoBench ACW
Standard ModeToolsInternet
81
5 / 20
MMMU
Thinking Enabled
79.60
19 / 74
VPCT
Standard Mode
40.50
13 / 24

Agentic Development

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
76.90
9 / 59

Long Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
Fiction.liveBench
Standard Mode
66.70
13 / 16
Compare with other models