Back to the index
Google DeepMind · Gemini
No. 13

Gemini 3.1 Pro

Top-tier reasoning, knowledge and vision with a 1M-token multimodal context.

FrontierClosed weightsText, Image, Audio, Video, Pdf
Field notes
Context window
1.0Mtokens
Max output
66Ktokens
Input price
$2/ 1M tokens
Output price
$12/ 1M tokens
Cached input
$0.20/ 1M tokens
Modalities
Text, Image, Audio, Video, Pdf
Knowledge cutoff
Jan 2025
Released
Feb 2026
Approx. speed
Overview

What this model is

Gemini 3.1 Pro is Google DeepMind's flagship, benchmarking at or near the very top on knowledge, math, science and multimodal understanding, with an enormous 1M-token context window. It is a superb research, analysis and vision model — but in long autonomous coding sessions it is materially less reliable than the Claude/GPT frontier, and can derail, loop, or corrupt a codebase over a few prompts. Excellent for knowledge work and multimodal reasoning; use with supervision for extended agentic coding.

Strengths

  • Elite math, science and knowledge benchmarks
  • Best-in-class multimodal (image/video/PDF) understanding
  • 1M-token context for huge documents and codebases
  • Strong single-shot reasoning and planning

Trade-offs

  • Less reliable than Claude/GPT on long agentic coding
  • Can derail, loop, or corrupt a codebase over multiple prompts
  • Higher latency than the Flash tiers
  • Output capped at ~64K tokens

Best for

  • Deep research and analysis
  • Multimodal reasoning over images, video and PDFs
  • Long-context document synthesis
  • Math and science problem solving

Not ideal for

  • Unsupervised long-horizon coding agents
  • Latency-sensitive high-volume traffic
Capabilities

Capability profile

Normalized 0–100 scores, comparable across the whole catalog.

Reasoning90Coding78Math94Writing89Knowledge94Speed60Agentic76Vision95Multilingual92Long Context96
Reasoning
90
Coding
78
Math
94
Writing
89
Knowledge
94
Speed
60
Agentic
76
Vision
95
Multilingual
92
Long Context
96
Benchmarks

How it scores

Public benchmark results, with independent third-party results where available. Bars normalize percentages to 100 and Elo ratings to a 1500 ceiling.

Independent index
Artificial Analysis Intelligence Index
Composite of ~9–10 independent evals · Artificial Analysis
46/ 100
BenchmarkResult
Artificial Analysis Intelligence Indexindependent
GeneralArtificial Analysis
46%
SWE-bench Verifiedindependent
CodingSWE-bench
80.6%
SWE-bench Proindependent
CodingSWE-bench Pro
46.1%
τ-benchindependent
Agenticτ-bench
76.5%
GPQA Diamondindependent
ReasoningIndependent aggregators
94.3%
MMLU-Pro
KnowledgeVendor-reported
80.5%
AIME 2025
MathVendor-reported
95%
MMMU
VisionVendor-reported
81%
LiveBenchindependent
GeneralLiveBench
79.9%
LMArena Eloindependent
GeneralLMArena
1505Elo
Alternatives

Comparable models

Models in a roughly similar class — worth weighing against this one.