Google Argon Report - GraphWalks BFS 256k to 1M: leaderboard
Google Gemini 4 Argon October 2026 release report. All models: 200 GraphWalks items from 256k to 1M tokens; BFS F1. All four models evaluated by Google. Maximum available or best available reasoning, with exact peer API effort unreported; not interchangeable with borrowed leaderboard rows.
Metric: Score (%). Source: deepmind.google. Saturation forecast: Around March 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 84.2 | #7 |
| 2 | GPT-6 Astra | 71.8 | #5 |
| 3 | Claude Opus 5.5 | 66.8 | #3 |
| 4 | Claude Fable 5.1 | 65 | #9 |
No result here: #8 GPT-6.1 Sol, #10 Claude Sonnet 5.5.
Interactive version: theaggregate.ai/benchmark?slug=google-argon-report-graphwalks-bfs-256k-to-1m · How It Works · Data refreshed daily, snapshot 2026-10-16.