BlenderBot 9.4B
READER SUMMARYMeta's 9.4-billion-parameter open-domain dialogue model, publicly released with weights, code, and evaluation tooling through ParlAI.
Why this model scores 25.5
The model was historically large and broadly generative for open-domain dialogue, with public weights increasing diffusion and misuse access. It had negligible independent agency, substantial hardware requirements, research-oriented deployment, and acknowledged but limited safety controls.
News tied to BlenderBot 9.4B
The model score of 25.5 rates this model's risk profile. The overall Doom Index of 60.7 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.
Meta open-sources the 9.4B BlenderBot dialogue model and recipe
Meta released the complete 9.4-billion-parameter BlenderBot model, code, and evaluation setup through ParlAI. The largest publicly released open-domain chatbot at the time blended knowledge, empathy, and personality, while Meta acknowledged hallucination, contradiction, repetition, and unresolved harmful-language risks.
- Full item contribution
- +0.01
- BlenderBot 9.4B equal share
- +0.01
Model score history
- R1Doom Score 25.5
New exact source-verified historical open model absent from the durable catalogue.
11 Aug 2026