Offloop says its 3B dispatcher beats Codex and Claude Code on GDPval at $1.65 a task
dr_cintas · x · 2026-07-24
Offloop says its new multi-agent system beats Codex and Claude Code on real-work benchmarks.
According to the post, the system uses a 3B-parameter dispatcher called D1 to decide which agent should act next — and, just as importantly, which agents should stay quiet. On the same 220 GDPval tasks, it reports costs of $1.65/task versus $5.20/task for Codex and $14.38/task for Claude Code. The team says the project was built by people who left Manus.
Related event: Offloop's Multi-Agent Framework Tops GDPval Benchmark(10 posts)→
More from coding & agent
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- Codex tip: use Sol with Astra and Luna sub-agents to save usage — pvncher · 2026-09-11
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Agile co-author Ron Jeffries publishes 'Resist AI', urging developers to push back — mborch · 2026-09-11