WHAT NEW IN X11.03 TUE

AI collections from X · 22 collections · 66,612 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 1 hour ago
gpt-6IMAGE

GPT-6 Astra tested on 29 tasks across 6 agent harnesses

Composio ran Astra through six agent harnesses including Codex and Claude Code on 29 hard tasks; success rates were similar, but failures consumed 3–5x more tokens.

Composio
@composioArchived 2026.09.17Originally posted 2026.09.17
GPT-6 Astra tested on 29 tasks across 6 agent harnesses
Composio @composioOriginally posted 2026.09.17
Open original on X

We ran GPT-6 Astra across 6 agent harnesses (Codex, Claude Code, OpenCode, Hermes Agent, Pi Agent, Command Code) on 29 challenging agentic tasks. Most harnesses succeeded at similar rates. But when they failed, they used 3–5x as many tokens, depending on the harness. 🧵🧵🧵

x.com/composio/status/2100308380980068538Archived 2026.09.17 10:17
Open original on X