Compare Start here

Google DeepMindLanguage modelSuperseded

Gemini 3.1 Pro

Doubled Gemini 3's reasoning scores and topped GPQA for months.

Compare head-to-head Race it in 3D

Overall Intelligence

#15

of 56
6.4 pts behind #1

0

races led

354

weeks at #1

82.3

score

Released: Feb 19, 2026; 8 mo ago
Context: 1M; 65K max output
Price: $2 / $12; per 1M in/out · $4.50 blended
Speed: 110 tok/s; 7s to first token
Modalities: text · image · audio · video; outputs text
Weights: Closed; API and apps

The 30-second version

Doubled Gemini 3's reasoning scores and topped GPQA for months.

Key takeaways

1Doubled Gemini 3's reasoning scores and topped GPQA for months.

Where it ranks

Current snapshot · illustrative scores · click any race to watch it

3.1 ProBest on each axis

Overall

15Overall+6.4 pts

Coding

21Coding+10.7 pts 17Frontend & UI+53 Elo 21Backend & APIs+9.8 pts 16Distributed Systems+10.6 pts 25Full-Stack Apps+12.8 pts 19Debugging & Repair+10.3 pts 24Agentic Coding+13.4 pts 19Code Review & Security+9.5 pts 19Data Science & SQL+7.8 pts 24Mobile Apps+10.1 pts 25Terminal & DevOps+15.2 pts 18Competitive Programming+267

Hard Reasoning

16Hard Reasoning+7.9 pts 14Frontier Questions+11.6 pts 16Abstract & Novel Reasoning+10.5 pts 17Logic & Puzzles+7.0 pts 21Planning & Strategy+9.8 pts

Math

17Math+8.8 pts 16Competition Math+7.1 pts 17Research Math+11.7 pts 17Applied & Quantitative+7.0 pts

Science

13Science+6.9 pts 16Graduate Science QA+4.8 pts 12Biology & Medicine+6.4 pts 11Physics & Chemistry+4.6 pts 16Research Assistance+7.3 pts

Writing & Language

19Writing & Language+9.6 pts 22Creative Writing+70 Elo 22Technical Writing+9.3 pts 18Editing & Style+7.2 pts 13Multilingual+4.6 pts 20Instruction Following+7.6 pts 21Conversation & EQ+65 Elo

Multimodal

4Multimodal+7.2 pts 7Image Understanding+5.3 pts 8Documents & Charts+6.3 pts 2Video Understanding+6.7 pts 6Speech & Audio+6.0 pts

Tool Use & Agents

20Tool Use & Agents+11.3 pts 26Tool Use+9.8 pts 15Computer Use+14.0 pts 18Web Research+13.3 pts 26Long-Horizon+22.7 hrs

Long Context

9Long Context+6.0 pts 121M Recall+6.3 pts 8Long Reasoning+3.8 pts

Speed & Cost

29Speed & Cost+41.8 pts 17Output Speed+413 tok/s 46Latency+6.68s 25Cost-Efficiency+43.7 pts

Trust & Factuality

18Trust & Factuality+10.4 pts 20Factuality+9.0 pts 18Honesty & Calibration+8.2 pts

Overall Intelligence over time

#1 frontier3.1 Pro3.5 FlashKimi K3

Update history

The distilled version first; open any release for the deeper breakdown.

The Gemini Pro family

2.5 ProMarch 2025 Gemini 3 ProNovember 2025 3.1 ProFebruary 2026 Gemini 4 ArgonOctober 2026

60-second briefing

3.1 Pro, explained

AI video summary · placeholder render from the auto-written script

From Google's own guide, distilled

Gemini prompt design strategies

Structure prompts as persona, task, context and format; the format line is the most often forgotten.
Few-shot examples set the pattern; keep their formatting identical so the model copies structure, not noise.
Gemini reads images, video and PDFs natively, so attach the source instead of describing it.
Place media before the text instruction that refers to it.
Break complex jobs into a chain of smaller prompts and pass outputs forward.

All official guides, distilled →

About Google DeepMind

Google's AI lab behind Gemini, Veo, Imagen and Nano Banana.

Optimising for

Native multimodality (image, video, audio), very long context, science, and tight integration with Search, Workspace and Android.

London, UK / Mountain View, US · founded 2010

Closest rivals

3.1 Pro is 15th in overall intelligence; leader is Claude Opus 5.5.