OpenAI's New API Harness Boosts GPT-5.6 Score by 188% Using 6x Fewer Tokens
arthurcolle · x · 2026-07-30
OpenAI demonstrated the latest test results of its Responses API. By applying a new harness engineering setup (featuring retained reasoning and context compaction), the GPT-5.6 Sol model achieved a 188% score increase on the public set, while reducing output token consumption by 6x.
Researcher Nathan Lambert pointed out that there is immense low-hanging fruit in harness engineering. Deeply studying the effect of harnesses from post-training through eval and inference will become a highly impactful area, significantly optimizing model cost savings per performance.
Related event: Optimized Memory Settings Triple GPT-5.6's Score on ARC-AGI-3(27 posts)→
More from coding & agent
- 10 open-source repos that let your AI agent reverse-engineer apps and games — victor_explore · 2026-10-16
- The new CTO job: agent management and QA loops, 'cable management' instead of coding — HankYeomans · 2026-10-16
- Why company AI agents go stale: adoption needs in-house knowledge, not just better agents — EdenEmarco177 · 2026-10-16
- Open-source MCP lets coding agents search Obsidian's 9,000-plugin directory before reinventing wheels — pitfa19 · 2026-10-16
- Cheng Lou open-sources Handwired: hand-written weights turn code into training-free neural nets — dotey · 2026-10-16
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16