DataLearner logo

Gemini 3.0 Pro (Preview 11-2025) Benchmark Details

Gemini 3.0 Pro (Preview 11-2025) currently shows benchmark results led by MMLU Pro (2 / 132, score 90), LiveCodeBench (2 / 123, score 92), GPQA Diamond (5 / 187, score 93.80). 1 source link is attached for reference.

Benchmark Results

Gemini 3.0 Pro (Preview 11-2025)

Benchmark Results

Thinking
Tool usage

General Knowledge

14 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
93.80
5 / 187
GPQA Diamond
91.90
14 / 187
GPQA Diamond
91
17 / 187
MMLU Pro
90
2 / 132
ARC-AGI
87.50
19 / 67
ARC-AGI
75
26 / 67
LiveBench
Thinking Level · Low
63.90
54 / 115
LiveBench
Thinking Level · High
73.39
24 / 115
HLE
45.80
38 / 170
HLE
41
58 / 170
HLE
37.50
67 / 170
HLE
37.20
68 / 170
ARC-AGI-2
45.10
25 / 61
ARC-AGI-2
31.10
31 / 61

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
72.10
6 / 47

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
92
2 / 123
SWE-bench Verified
76.20
35 / 111

Math and Reasoning

5 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
95
25 / 107
AIME 2026
90.60
14 / 18
FrontierMath
38
10 / 60
FrontierMath - Tier 4
Standard Mode
18.80
16 / 80
FrontierMath - Tier 4
18.80
16 / 80

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Thinking Mode
76.40
5 / 63

Agent Level Benchmark

4 evaluations
Benchmark / mode
Score
Rank/total

Instruction Following

2 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
70
13 / 30
IF Bench
70
13 / 30

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
59.20
37 / 52

AI Agent - Tool Usage

3 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Standard ModeTools
70.30
15 / 27
Terminal Bench 2.0
56.90
25 / 47
Terminal Bench 2.0
54.20
29 / 47

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA
35
18 / 21

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
71
2 / 14

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
70.70
31 / 37
Compare with other models

Sources

artificialanalysis.aiartificialanalysis.ai