# Arena.ai places GPT-6 Sol (Max) sixth on Agent Arena at +7.7% and $0.75 per task

Arena.ai says OpenAI’s GPT-6 Sol (Max) recorded a +7.7% net improvement across 4,000+ real-world agentic sessions, at a median cost of $0.75 per task. It trails Claude Fable 5 (High) by 0.60 percentage points while costing 56% less per task.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T06:47:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/cf04e6a664d1474fb69b187c.html

Content language: en
Localization state: sameLanguage

Source: Arena.ai · Published 9/25/2026, 12:58:43

Arena.ai says OpenAI’s GPT-6 Sol (Max) is sixth in Agent Arena, with a +7.7% net improvement across 4,000+ real-world agentic sessions from its user community. On Arena.ai’s Pareto frontier, the median cost is $0.75 per task, 0.60 percentage points below Claude Fable 5 (High) at +8.3% and 56% below that model’s $1.72 per task.

Against GPT 5.6 Sol (xHigh), Arena.ai reports net improvement of +7.7% versus +6.2%, a rank move from No. 8 to No. 6, and half the per-token price. On Confirmed Success, it places GPT-6 Sol (Max) fourth at +11.4%, compared with No. 20 and 2.9% for GPT 5.6 Sol.

Tags: GPT-6 Sol, Agent Arena, OpenAI, Arena.ai, Model evaluation

[View original post](https://x.com/arena/status/2103572481206538439)