Google

Gemini 3.1 Pro

Adjustable Deep Think; agentic browsing (BrowseComp 85.9)

Vendor
Google
License
closed
Released
2026-03
Parameters
Undisclosed
Context window
2M tokens

Capabilities

Gemini 3.1 Pro supports vision (image input), audio input, tool use, extended reasoning and computer use, with a 2M-token context window.

  • Vision — image input
  • Audio — audio input
  • Tools — function calling / tool use
  • Reasoning — extended thinking
  • Computer use — desktop / browser control

Benchmarks

SWE-Bench Verified 78%
SWE-Bench Pro Not published
Terminal-Bench Not published
Reasoning composite 94 / 100

The reasoning composite is a directional 0–100 score aggregated across public reasoning evals — comparable within this matrix, not an official vendor number.

Pricing

$7/M input tokens.

Links