Google · model sentiment

Gemini 3.1 Pro Preview

Community placement across every tier-bench category
#6overall community rank

Where people place it

The complete spread matters more than the average. A wide distribution usually means the model is polarising or used for very different jobs.

S
0%
A
0%
B
0%
C
0%
D
0%
E
0%
F
0%

Across the benches

Overall#60.00 community score
Chatting#60.00 community score
Math#60.00 community score
Code quality#60.00 community score
Steerability#60.00 community score
Most value#60.00 community score

What people are saying

Comments are anonymous by default. Members can deliberately attach their handle.

No comments yet. Start with what it is actually like to use this model.

Facts, for reference

Model details

Released / listedFeb 19, 2026
Context1.0M tokens
Inputaudio, file, image, text, video
OpenRouter input$2.0 / 1M

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

View source ↗