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 Real Task Execution(5 posts)→
More from coding & agent
- Blogger builds satellite-imaging financial due diligence tool on Doubao Seed 2.1 — karminski3 · 2026-09-16
- Reading agent-written code: 'corrigibility' has become a matter of faith — daniel_mac8 · 2026-09-16
- NoSpoon agent churns out "so bad it's good" AI slopdrama in ten minutes, site closing soon — Kyrannio · 2026-09-16
- Dev who tested AI PR review bots says CodeRabbit is the worst: spammy promo and wild hallucinations — uwukko · 2026-09-16
- Existing AI PR review bots failed on helium, so this dev built one that catches bugs from day one — uwukko · 2026-09-16
- TypeSafe Jev early-access test: 5.7x faster responses, 98% lower cost, +12pp accuracy — jon_reed · 2026-09-16