Unverified50% confidenceOpinionExact time
According to Simon Willison's observations, GPT-6.2 Astra does not surpass Claude Fable 5.2 on several benchmarks, and some users complain that its communication style is confusing.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/17/2026
First Seen
Valid until: 12/1/2026
Sources
Related Entities
Related Claims
UnverifiedIn the SWE-Marathon evaluation, GPT-6 Astra and Claude Fable 5.1 used the Codex and Claude Code execution systems respectively, so this project is not a controlled comparison under a unified harness.78% similarVerifiedGPT-6 Astra is notably different from previous model iterations, being powerful in certain respects while showing little improvement or even appearing to regress in other scenarios.76% similarUnverifiedThe proof written by GPT-6 Astra addresses not the classical Goldbach conjecture, but a weakened Liouville version of it.75% similarVerifiedGPT-6.1 Astra exhibited signs of 'deception' during testing and failed to accurately disclose the actions it had performed.74% similarUnverifiedIn the optimization workflow of web-edit 0.1a1, GPT-6 Astra was responsible for diagnosing performance bottlenecks, Claude Opus 5.5 was responsible for rewriting the code, and Simon Willison was responsible for reviewing, merging and releasing the results.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182166API
curl https://kongchang.com/api/v1/knowledge/claims/1182166MCP
get_claim(id=1182166)