#2
Gemini 3.1 ProNew
gemini-3.1-pro-preview
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 85 tok/s
Release Date
February 19, 2026
Lab
Google DeepMind
Type
Proprietary
Context Size
1M
Max Output Tokens
65.5K
Cost per 1 million tokens
$2.00 / $12.00
Model Inputs*
Text, Images, Audio, Video
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
91.72 pts
Rank #2
98th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Gemini 3.1 Pro sets a new standard for comprehension with a dominant 77.1% on ARC-AGI-2, far outpacing competitors. It excels in complex reasoning and "vibe coding," making it a top choice for creative and technical projects. While its "direct" style results in a moderate empathy score (82.50), its massive 1M context window and fast generation speed make it a powerhouse for heavy workloads.

Intelligence

Overall Score; Higher is better

Claude Opus…
Gemini 3.1 …
Claude Opus…
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3
GPT 5.2
GLM 5
GPT 5

Speed

Output Tokens per Second; Higher is better

DeepSeek V3…
GLM 4.7 Fla…
Gemini 2.0 …
Grok 4 Fast…
Llama 3.3 7…
Gemini 3.1 …
DeepSeek V3
ChatGPT 4o
GPT 4o
Grok 3 Mini

Price

USD per 1M Tokens; Lower is better

o4-mini
o3-mini
GPT 5.1
GPT 5
GPT 5.2
Gemini 3.1 …
Gemini 3 Pro
o3
Gemini 2.5 …
GPT 4o

Google Models

Overall Score; Same provider comparison

Gemini 3.1 …
Gemini 3 Pro
Gemini 2.5 …
Gemini 3 Fl…
Gemini 2.5 …
Gemini 2.0 …
Gemini 2.5 …
Gemini 2.0 …

Gemini Family

Overall Score; Same model family comparison

Gemini 3.1 …
Gemini 3 Pro
Gemini 2.5 …
Gemini 3 Fl…
Gemini 2.5 …
Gemini 2.0 …
Gemini 2.5 …
Gemini 2.0 …

Closest Rivals

Overall Score; Nearest by overall rank

Claude Opus…
Gemini 3.1 …
Claude Opus…
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3
GPT 5.2
GLM 5
GPT 5