Apodex 1.1 turns deep research into real execution; FrontierChallenge shows 20.6% max completion
alifcoder · x · 2026-08-28
Apodex 1.1 pushes "deep research" toward actual execution: working across files, combining search + code, coordinating multiple agents in parallel, and adapting when the task changes mid-way without discarding valid progress.
Releases include the open-source FrontierAgent repo, an open Apodex 1.1 mini (35B), a web app, and an API.
The accompanying FrontierChallenge benchmark (#2 on Hugging Face Daily Papers) tests whether agents can complete real scientific workflows end to end with verifiable results: across 12 frontier models and 97 cross-domain tasks, the best full-completion rate was only 20.6% (GPT-5.6 Sol + Codex and Grok 4.6 + Claude Code); in electrochemistry and environmental science, every system scored 0%.
More from coding & agent
- Dev vibe-codes open-source newsletter platform, 83% cheaper than Beehiiv from $19/mo — marclou · 2026-10-15
- ERP AI launches Proto: 'headless SaaS' business software built for AI agents — Aiden_Tech_Ai · 2026-10-15
- FLUX.3 Image Klein ships open in Diffusers: layout control, 2s per image on H100 — ariG23498 · 2026-10-15
- Engineering managers need deep reading, not just agent summaries: 5 recommended resources — rseroter · 2026-10-15
- Adding motion graphics with just a prompt: the Claude Motion x ElevenLabs MCP workflow — CurieuxExplorer · 2026-10-15
- A $15k AI SEO client-finding system built on Claude, free to download — aryanXmahajan · 2026-10-15