Gemini 3.1 Pro more than doubles its predecessor's ARC-AGI-2 score
- Source
- x.com
- Date
Introducing Gemini 3.1 Pro 🚀 3.1 Pro represents a major step forward in core reasoning. It scored 77.1% (more than doubling 3 Pro’s score) on ARC-AGI-2, the benchmark that evaluates a model's ability to solve new logic patterns and work through challenges it hasn’t encountered before. This demo illustrates how the model can go beyond the prompt. Instead of rendering a video or static graphic, 3.1 Pro codes a full environment, integrating generative audio and providing UI controls.
We're shipping 3.1 Pro across our consumer and developer products to bring this advancement in intelligence to your everyday applications. Start building your ideas into reality today!
Read our blog to learn more about the model ⬇️ https://t.co/1VPrenVSua
Context
Gemini 3.1 Pro's headline reasoning improvement refers to a specific test of unfamiliar logic patterns. Google DeepMind's model card reports 77.1% on ARC-AGI-2, compared with 31.1% for Gemini 3 Pro, with both models using high thinking effort. The results are labeled ARC Prize Verified.
That is a substantial improvement on the 's abstract-reasoning puzzles. It supports a narrower conclusion than saying the model is twice as capable at every task: the measured gain concerns this , while coding, research and other uses require their own evidence.
- benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
- postGoogle's week: EmbeddingGemma 2, Nano Banana 2.1, Gemini business agent
postGoogle opens SynthID watermark checks to everyone, with partner coverage
postGemma 4 orchestrates a plant DNA model to find crop mutations in minutes
articleGoogle's Project CC gives a family agent its own identity and sandbox
Checking sign-in…
Loading comments…