Gemini 3 Pro Benchmark Details

Gemini 3 Pro currently shows benchmark results led by VPCT (1 / 24, score 91), BALROG (1 / 12, score 58.10), MedCode (10 / 64, score 52.20).

Benchmark Results

Gemini 3 Pro

Benchmark Results

Writing

1 evaluations

Benchmark / mode

Score

Rank/total

Creative Writing

Standard Mode

1524.50

52 / 110

Service Workflows

3 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Thinking Level · HighTools

91.01

16 / 30

SAGE

Thinking Level · HighTools

47.62

24 / 64

τ³-Banking

Thinking Level · HighTools

18.04

97 / 167

Mathematics

1 evaluations

Benchmark / mode

Score

Rank/total

IMO-ProofBench Advanced

Thinking Enabled

7 / 24

Agentic Development

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 2.1

Thinking Level · HighTools

73.93

37 / 57

Maintenance & Optimization

1 evaluations

Benchmark / mode

Score

Rank/total

GSO

Standard ModeTools

18.60

11 / 21

ML Engineering

1 evaluations

Benchmark / mode

Score

Rank/total

WeirdML v2

Standard ModeTools

69.93

19 / 52

Visual Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

VPCT

Standard Mode

1 / 24

GeoBench ACW

Standard Mode

4 / 20

Preference Arenas

1 evaluations

Benchmark / mode

Score

Rank/total

Text Arena (Coding)

Standard Mode

1471

22 / 35

Logical Planning

1 evaluations

Benchmark / mode

Score

Rank/total

BALROG

Standard ModeTools

58.10

1 / 12

Capability Frontier Metrics

1 evaluations

Benchmark / mode

Score

Rank/total

METR Time Horizons v1.1

Standard ModeTools

224.33

8 / 22

Honesty & Factuality

1 evaluations

Benchmark / mode

Score

Rank/total

AA-Omniscience

unknown

15.30

1 / 3

Code Generation & Editing

1 evaluations

Benchmark / mode

Score

Rank/total

Vibe Code Bench v1.1

Thinking Level · HighTools

14.30

52 / 61

Clinical Workflows

2 evaluations

Benchmark / mode

Score

Rank/total

MedScribe

Thinking Level · HighTools

72.04

58 / 66

MedCode

Thinking Level · HighTools

52.20

10 / 64

Capability Indices

1 evaluations

Benchmark / mode

Score

Rank/total

ECI

unknown

152.96

36 / 167

Compare with other models