LMArena adds GPT-6 Astra for testing in Battle and Agent modes
arena · x · 2026-09-05
LMArena announced that GPT-6 Astra is now testable on its leaderboard platform in two modes: Battle Mode for blind side-by-side comparison and Agent Mode targeting its long-horizon agentic strengths. The platform also offers scenario entry points including image editing, landing page generation, dashboards, playable games, design-to-code, and fullstack app building — a public channel for third-party evaluation of the new flagship.
Related event: LMArena Adds GPT-6 Astra in Battle and Agent Modes(2 posts)→
More from Models
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- qev-0.8B: a tiny local decision model that picks moves in 3.5ms on 1.3GB — fajfas3 · 2026-10-21