Apodex 1.1 launches: moves from deep research to real task execution
testingcatalog · x · 2026-09-16
Apodex has released 1.1, a model family that shifts from deep research to actually executing long-horizon tasks. It can work directly with uploaded files, search, and code environments, and produces files where every claim is traced back to its source.
With the Agent Team configuration, Apodex 1.1 more than doubles its 1.0 scores on APEX-Agents, FrontierScience-Research, and BioMysteryBench.
Related event: Apodex 1.1 shifts from research Q&A to end-to-end task execution(5 posts)→
More from coding & agent
- Microsoft's MemSteer turns unlabeled user histories into agent memory supervision — MicrosoftResearch · 2026-11-02
- She fired herself from her own Instagram: AI agent runs the account, views up 82.3% — heyshrutimishra · 2026-11-02
- Sourcegraph: AI writes code faster than teams can review it, driving more outages — AI Engineer · 2026-11-02
- Tsinghua & Microsoft's HarnessMM cuts agent token use by up to 87.93% while raising success rate — rohanpaul_ai · 2026-11-02
- GitHub launches Agent HQ: Anthropic, OpenAI, Google coding agents in Copilot — emmanuelvivier · 2026-11-02
- DeepSeek open-sources Super-Agent, a coding agent that reads team chats to minimize human input — emmanuelvivier · 2026-11-02