OpenAI reportedly quietly edited GPT-6 Astra benchmark results
A Fortune report reveals OpenAI quietly edited GPT-6 Astra benchmark figures after launch, halving its hallucination rate to 2% and lowering a competitor's scores, raising transparency concerns.
2026-09-05 ~ 2026-09-06 · 4 related posts
- Episode 1: OpenAI launches flagship GPT-6 Astra to rave reviews and pricing debates(2026-09-04, 190 posts)
- Episode 2: GPT-6 Astra saturates ARC-AGI-3 with near-perfect scores and near-zero reasoning tokens(2026-09-04, 10 posts)
- Episode 3: OpenAI Engineer: Token-Based Pricing Is Broken, Cost Should Be Measured Per Task(2026-09-04, 4 posts)
- Episode 4: OpenAI reportedly quietly edited GPT-6 Astra benchmark results(2026-09-05, 4 posts)
- Episode 5: Users Report GPT-6 Astra Hits New SOTA in Agentic CAD(2026-09-05, 2 posts)
- Episode 6: GPT-6 Astra reportedly runs Blender for 5 hours on 3D modeling(2026-09-06, 2 posts)
- Episode 7: Astra's Record Debut Reportedly Pushes OpenAI to Accelerate Roadmap(2026-09-06, 2 posts)
- OpenAI quietly boosted GPT-6 Astra benchmark numbers and kept changing them after launch, Fortune reports — jeremyakahn · 2026-09-05
- OpenAI quietly changed GPT-6 Astra benchmark results around launch, Fortune reports — mark_k · 2026-09-05
- OpenAI quietly rewrote GPT-6 Astra's eval numbers hours after publishing its launch post — 新智元 · 2026-09-06
1 near-duplicate retellings: mark_k