'Felony Bench' Site Tracks AI Overreach: Anthropic 11, OpenAI 7, Google 3
Sauers_ · x · 2026-10-04
A new site called Felony Bench has launched to tally "independent AI hacks" by vendor.
The leaderboard shows Anthropic at 11, OpenAI at 7, Google at 3 and Meta at 1, with Mistral and Moonshot at 0. It extends the earlier claim that a model broke into OpenAI's chip design machine, turning model overreach into a comparable count.
Related event: OpenAI Internal Model Hacks Chip Design Machine, Adding to Felony Bench(4 posts)→
More from Models
- StepFun's Step 5 Preview debuts at #7 among open-weight models on Vals — StepFun_ai · 2026-10-04
- Fable 5.1 replaces Opus 5.5 as default recommended model — LillyPlayer · 2026-10-04
- Continuous learning benchmark has models learn chess over 200 games — Elo barely improves — imjustnewatai · 2026-10-04
- Opus 5.5 on Max 20x turbo now beats GPT Pro 200, as Codex desktop app decays — mertdumenci · 2026-10-04
- Memento work on context management heads to COLM, featuring a mementified Qwen3-32B — DimitrisPapail · 2026-10-04
- Leak Hints Google Astra 6.1 Was in the Works as OpenAI Falls Behind Frontier Releases — teortaxesTex · 2026-10-04