Skip to main content

Gemini 3.1 Pro Preview

GoogleGeminiProprietary

Description

Gemini 3.1 Pro is the latest model in the Gemini 3 series. It excels at complex tasks requiring broad world knowledge and advanced reasoning across modalities. Gemini 3.1 Pro uses dynamic thinking by default to reason through prompts, and features a 1 million-token input context window with 64k output tokens.

Release Date
2026-02-19
Parameters
Context Length
1.0M
Modalities
audio, file, image, text, video

Capability Radar

55
general
56
coding
94
reasoning
72
scienceest.
80
agents
80
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agents & Tools26
65.0
LS
Code Ranking5
93.0
AA
General Ranking2
95.0
AA
Reasoning35
77.0
LS
Science1
100.0
AA

Benchmark Scores (LLM Stats)

Agents

GDPval-AA1317.00 / 3000SR
t2-bench99.3%SR
BrowseComp85.9%SR
MCP Atlas69.2%SR
Terminal-Bench 2.068.5%SR
SWE-Bench Pro54.2%SR
APEX-Agents33.5%SR

Biology

GPQA94.3%SR
SciCode59.0%SR

Code

LiveCodeBench Pro2887.00 / 3000SR
SWE-Bench Verified80.6%SR

General

MMMLU92.6%SR
MMMU-Pro80.5%SR
MRCR v2 (8-needle)26.3%SR

Math

Humanity's Last Exam51.4%SR

Reasoning

ARC-AGI v277.1%SR

AA Evaluation Indices

Intelligence Index
57.2
Coding Index
55.5
Tau2
1.0
Gpqa
0.9
Ifbench
0.8
Lcr
0.7
Scicode
0.6
Terminalbench Hard
0.5
Hle
0.4

LLM Stats Category Scores

Finance
100
Legal
100
General
100
Code
100
Reasoning
100
Agents
100
Language
90
Search
90
Spatial Reasoning
80
Tool Calling
80
Biology
80
Chemistry
80
Frontend Development
80
Multimodal
80
Physics
80
Vision
70
Math
70
Long Context
30
Healthcare
20

Pricing

Input Price$2 / 1M tokens
Output Price$12 / 1M tokens
Blended Price (3:1)$4.5 / 1M tokens

Speed

Tokens/sec130.3 tokens/s
Time to First Token28.61s
Time to Answer28.61s

Available Providers

(LS internal units)
ProviderInput PriceOutput Price
Google2.5M15.0M

External Sources