---
format: "aidr-story-markdown/v1"
id: "6821b2cb65ab380d05484aeb434c4325516e137cd33c19f4d005b9de6d674094"
canonical_url: "https://aidr.today/6821b2cb?lang=en"
title: "Google's Gemini 4 Hydrogen Beats Larger Argon Model at a Fifth of the Task Cost"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-12T19:07:00.000Z"
category: "Models"
topics: ["google","llm"]
source_urls: ["https://huggingnews.com/ai/googles-gemini-4-hydrogen-beats-larger-argon-model-at-a-fifth-of-the-tas-682e8af5","https://x.com/sundarpichai/status/2120940236805169182","https://x.com/cursor_ai/status/2120944639633211619","https://x.com/Hesamation/status/2120951643386593727","https://x.com/ChrisGPT/status/2120946632816541738","https://x.com/osanseviero/status/2120941462808559905","https://x.com/arena/status/2120940869889175840","https://x.com/levie/status/2120947988143198302"]
summary: "Google's Gemini 4 Hydrogen model launched at fifth place on Agent Arena with a median completion time of 5.3 minutes per task and a median cost of $1.60, running 3x faster and 4.7x cheaper per task than top-ranked Claude Fable 5.2. On Artificial Analysis evaluations, Hydrogen's default high reasoning setting matches the 51 Intelligence Index score of Google's larger Gemini 4 Argon model at 19% of the cost per task ($1.87) and a 62.5% lower token price, while its new xhigh setting reaches 54 at $3.16 per task, one point behind Claude Sonnet 5.5 at 32% of its cost. Hydrogen also recorded an 8% hallucination rate on AA-Omniscience, compared with 43% for Sonnet 5.5 and 52% for GPT-6.1 Sol."
---

# Google's Gemini 4 Hydrogen Beats Larger Argon Model at a Fifth of the Task Cost

> [Open the canonical story](<https://aidr.today/6821b2cb?lang=en>)

**Published:** 2026-11-12T19:07:00.000Z
**Category:** Models
**Topics:** google, llm

## Summary

Google's Gemini 4 Hydrogen model launched at fifth place on Agent Arena with a median completion time of 5\.3 minutes per task and a median cost of $1\.60, running 3x faster and 4\.7x cheaper per task than top\-ranked Claude Fable 5\.2\. On Artificial Analysis evaluations, Hydrogen's default high reasoning setting matches the 51 Intelligence Index score of Google's larger Gemini 4 Argon model at 19% of the cost per task \($1\.87\) and a 62\.5% lower token price, while its new xhigh setting reaches 54 at $3\.16 per task, one point behind Claude Sonnet 5\.5 at 32% of its cost\. Hydrogen also recorded an 8% hallucination rate on AA\-Omniscience, compared with 43% for Sonnet 5\.5 and 52% for GPT\-6\.1 Sol\.

## Sources

- [Story source](<https://huggingnews.com/ai/googles-gemini-4-hydrogen-beats-larger-argon-model-at-a-fifth-of-the-tas-682e8af5>)
- [Story source](<https://x.com/sundarpichai/status/2120940236805169182>)
- [Supporting source](<https://x.com/cursor_ai/status/2120944639633211619>)
- [Supporting source](<https://x.com/Hesamation/status/2120951643386593727>)
- [Supporting source](<https://x.com/ChrisGPT/status/2120946632816541738>)
- [Supporting source](<https://x.com/osanseviero/status/2120941462808559905>)
- [Supporting source](<https://x.com/arena/status/2120940869889175840>)
- [Supporting source](<https://x.com/levie/status/2120947988143198302>)