Gemini 4 Argon changelog

Gemini 4 Argon debuts 31st of 145 on EQ-Bench Creative Writing v3

In its first result on EQ-Bench Creative Writing v3, Gemini 4 Argon scored 1758 Elo, 31st of 145.

Vals Index: Sonnet 5.5 edges Opus 5.5 and Gemini 4 Argon

Vals AI's GDP-weighted index of finance, coding, legal and tax tasks ranks Claude Sonnet 5.5 first at 70.85%, Opus 5.5 at 70.18%, Gemini 4 Argon 69.24%, GPT-6 Astra 65.02% and GPT-6.1 Sol 63.94% as of October 21, 2026.

Arena text leaderboard: Gemini 4 Argon first, Opus 5.5 second, GPT-6 Astra 73rd

Arena's October 20, 2026 text leaderboard ranks Gemini 4 Argon (High) first at 1532 (4,900 votes), Claude Opus 5.5 (High) second at 1516, Claude Opus 5 (Max) fourth at 1509, Claude Sonnet 5.5 (xHigh) 28th at 1473, GPT-6.1 Sol (Max) 66th at 1443 and GPT-6 Astra (Max) 73rd at 1441.

Arena WebDev leaderboard: Opus 5.5 first, GPT-6 Astra second

Arena's October 19, 2026 WebDev leaderboard ranks Claude Opus 5.5 (Max) first at 1807 (2,925 votes), GPT-6 Astra (Max) second at 1774, Claude Sonnet 5.5 (xHigh) third at 1768, GPT-6.1 Sol (Max) fourth at 1753, Claude Opus 5 (Max) eighth at 1689 and Gemini 4 Argon (High) tenth at 1678.

Vals AI Terminal-Bench 4.0 with one harness: Opus 5.5 65.2%, Astra 59.6%, Argon 57.6%

Running every model in the same Mini-SWE-agent harness, Vals AI reports Claude Opus 5.5 at 65.15%, Sonnet 5.5 64.14%, GPT-6 Astra 59.60%, Gemini 4 Argon 57.58%, GPT-6.1 Sol 55.05% and Opus 5 53.53%. GPT-6.1 Sol cost $1.72 per test against $13.20 for Opus 5.5.

OpenClaw adds Gemini 4 Argon and makes it the Google setup default

OpenClaw v2026.10.5 adds Gemini 4 Argon through Google and Vertex and Gemini 3.8 Flash through Google. Rerunning Google API-key setup now picks Gemini 4 Argon as the primary model.

Who is affected:

OpenClaw users who connect Google models.

What to do:

Check your primary model after rerunning Google setup if you want to keep another default.

Epoch runs Gemini 4 Argon: 96.4% on GPQA Diamond, 86% on FrontierMath tiers 1-3

Epoch's benchmark data, with runs started October 13, 2026, records gemini-4-argon at high effort scoring 0.964 on GPQA Diamond, 0.860 on FrontierMath tiers 1-3 and 0.780 on FrontierMath tier 4. Its ECI is 166.45.

Gemini 4 Argon available in GitHub Copilot for Pro+ and above

Gemini 4 Argon is GA in Copilot for Pro+, Max, Business and Enterprise users (not Pro), billed at provider list pricing.

Gemini 4 Argon generally available in the Gemini API

gemini-4-argon is GA on the paid tier of the Gemini API, with a unified 1,048,576-token context window, long decode up to 1M output tokens and thinking levels low, medium (default) and high. It is not available on the free tier.

Who is affected:

Developers who want Google's most capable model in the Gemini API.

What to do:

Raise max_output_tokens to at least 32,768 for existing apps, as Google recommends.

Gemini 4 Argon rolls out in the Gemini app for AI Pro and Ultra

Gemini 4 Argon is rolling out globally to Google AI Pro and Ultra subscribers in the Gemini app.

Gemini 4 Argon introductory price doubles on December 1, 2026

Argon launched at an introductory $2 per 1M input tokens and $10 per 1M output tokens through November 30, 2026. From December 1, 2026 the price is $4 input and $20 output, and context caching rises from $0.10 to $0.20.

Takes effect Dec 1, 2026 · in 30 days

Who is affected:

Paid Gemini API users of gemini-4-argon.

Action needed:

Budget for double the per-token cost from December 1, 2026.

Gemini 4 Argon announced for trusted cyber defenders first

Google announced its frontier model Gemini 4 Argon, rolling out first to trusted cyber defenders through its Fairwind Program, with an output limit raised to 1M tokens from 64K. Wider developer, enterprise and consumer access was to follow.