MazeBench Goes Free-to-Play Online; Schema Harness Hits Record 33% with GPT-6 Astra
patience_cave · x · 2026-10-14
MazeBench is now playable online for free. The benchmark also has a new coding-agent record: the Schema harness with GPT-6 Astra scores 33%, up from 23% with Codex — work by @guanningzeng and @HavenFeng.
A Gemini 4 Argon entry is coming soon, currently blocked by biology-related safety filters.
Related event: Schema with GPT-6 Astra Sets New MazeBench Record at 33%(2 posts)→
More from coding & agent
- FactoryAI launches OpenCompute, a self-hosted orchestrator for agent sandboxes in your VPC — annbordetsky · 2026-10-15
- shadcn praises Claude Code's clever 'Pin as chapter' feature — shadcn · 2026-10-15
- Team ships four developer guides for Gemini 4 Argon, incl. 1M-token long decode — patloeber · 2026-10-15
- Dev Creates Anthropic-Inspired Color Themes for IntelliJ — therealdanvega · 2026-10-15
- uv team split one giant crate into 14, cutting incremental Rust build times by 30-43% — charliermarsh · 2026-10-15
- Vercel found a simple filesystem beat their multi-agent system — plus 19 OSS agent tools — MaryamMiradi · 2026-10-15