OpenAI quietly boosted GPT-6 Astra benchmark numbers and kept changing them after launch, Fortune reports
jeremyakahn · x · 2026-09-05
Fortune reporter Emily Forlini reports that OpenAI has revised several evaluation benchmarks for its GPT-6 Astra model since publishing the launch blog post on Sept. 3 — in some cases making Astra's numbers better while figures for rival Anthropic's models got worse.
The rollout itself was rocky: the post was slated for 2 p.m. ET but took nearly two more hours to become widely viewable, and the link OpenAI's X account tweeted at 3:32 p.m. returned errors before CEO Sam Altman posted it himself, noting "We hit a little snag."
The report raises questions about vendor-reported benchmark integrity and post-launch metric manipulation.
Related event: OpenAI reportedly quietly edited GPT-6 Astra benchmark results(4 posts)→
More from Models
- X trends: SophontAI's Holon-S1 predicts gene activity from cancer slides; decision models rise — iScienceLuvr · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- 704-vote robotics Elo ranks Claude Opus 5.5 first at 1379; no model completes the task — qinzytech · 2026-10-21
- DeepSeek V4 called 'god-tier infra, 4th-tier ML': 7 tricks stacked, 20 patches to fix them — teortaxesTex · 2026-10-21
- GPT-6 Astra and Claude Fable 5.1 write $10,000 research papers — experts reject all — sayashk · 2026-10-21
- GitHub Copilot's HydraFusion Orchestrates Multiple Models Per Task — WirelessLife · 2026-10-21