Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
Gemini 3.1 Pro
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#36
83.5 points · 201 models
Research rank
#17
95 points · 195 models
Data coverage
212 items
24 sources · updated through 2026-09-02
Domain performance
Coding
#50 / 181
76.2
Research
#17 / 195
95
Agents
#50 / 147
76.2
Vision
#19 / 81
83.4
Long context
#22 / 95
83.8
Evaluation highlights
All evaluations
MMLU-Pro
Reasoning · DeepSeek-V4-Pro Technical Report
91%
1
/ 96
MMMU-Pro
Multimodal · Kimi K2.6 Technical Report
83%
1
/ 38
IFEval
Instruction following · LongCat-2.0 Technical Report
96.1%
1
/ 30
SciCode
Coding · Kimi K2.6 Technical Report
58.9%
2
/ 27
BrowseComp (w/ Context Manage)
Agents · GLM-5.1 Technical Report
85.9%
1
/ 13
MRCR v2 (8-needle 128K)
Long context · Google Gemini 3.6 Flash Official Release Evaluation
84.9%
4
/ 13
Basic information
Context (input / output)
1.05M / 66K
Release date
2026-05
Input modalities
Text · Image · Video · Audio
Output modalities
Text
Availability
Google
Full pricing
Input
$2 /1M
Output
$12 /1M
Related links
Official site
Version relationships
Gemini 3 family
Gemini 3 Pro
2025-11 · Same series
Gemini 3 Flash
2025-12 · Same series
Gemini 3.1 Flash-Lite Preview
2026-03 · Same series
Gemini 3.1 Pro
Current
2026-05 · Current model
Gemini 3.5 Flash
2026-05 · Same series
Gemini 3.5 Flash Cyber
2026-07 · Same series
Gemini 3.5 Flash-Lite
2026-07 · Same series
Gemini 3.6 Flash
2026-07 · Same series
Provider variants
Grounding · Preview