---
format: "aidr-story-markdown/v1"
id: "1a32b1d4f089f29c1653e33f0b5c2ccf6dc783b3f362b1d5402471071c175557"
canonical_url: "https://aidr.today/1a32b1d4?lang=en"
title: "Google Gemini 4 Argon Hits 97.5% to Become Second Lab to Top ARC-AGI-3"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-15T17:11:11.000Z"
category: "Models"
topics: ["google","reasoning","llm"]
source_urls: ["https://huggingnews.com/ai/google-gemini-4-argon-hits-975percent-to-become-second-lab-to-top-arc-ag-4fbef265","https://news.ycombinator.com/item?id=50118688","https://starskirmish.com/bench/v0-2/","https://the-decoder.com/googles-gemini-4-argon-is-closer-to-the-ai-frontier-than-any-google-model-in-months/"]
summary: "Google DeepMind's Gemini 4 Argon reasoning model has achieved 97.5% accuracy on the ARC-AGI-3 benchmark using a provider adapter harness costing $4.8K, making it the second AI lab to exceed 95% on the test. The model also scored 91.3% on ARC-AGI-2 and 98.5% on ARC-AGI-1, with François Chollet noting similarities to Astra's performance profile. Analysts attribute the improved scores to reinforcement learning, estimating an 85% probability that RL drove the result compared to a 15% chance for 'loopers.'"
---

# Google Gemini 4 Argon Hits 97\.5% to Become Second Lab to Top ARC\-AGI\-3

> [Open the canonical story](<https://aidr.today/1a32b1d4?lang=en>)

**Published:** 2026-10-15T17:11:11.000Z
**Category:** Models
**Topics:** google, reasoning, llm

## Summary

Google DeepMind's Gemini 4 Argon reasoning model has achieved 97\.5% accuracy on the ARC\-AGI\-3 benchmark using a provider adapter harness costing $4\.8K, making it the second AI lab to exceed 95% on the test\. The model also scored 91\.3% on ARC\-AGI\-2 and 98\.5% on ARC\-AGI\-1, with François Chollet noting similarities to Astra's performance profile\. Analysts attribute the improved scores to reinforcement learning, estimating an 85% probability that RL drove the result compared to a 15% chance for 'loopers\.'

## Sources

- [Story source](<https://huggingnews.com/ai/google-gemini-4-argon-hits-975percent-to-become-second-lab-to-top-arc-ag-4fbef265>)
- [Discussion](<https://news.ycombinator.com/item?id=50118688>)
- [Story source](<https://starskirmish.com/bench/v0-2/>)
- [Story source](<https://the-decoder.com/googles-gemini-4-argon-is-closer-to-the-ai-frontier-than-any-google-model-in-months/>)