OpenAI Test: Optimized Harness Boosts Model Scores by 188% with 6x Fewer Tokens
ChrisUniverse · x · 2026-07-31
OpenAI shared benchmark data on agentic harnesses. By implementing the Responses API with retained reasoning and context compaction, the GPT model's score on a public set surged by 188%.
Additionally, this optimized harness used 6x fewer output tokens, proving that engineering wrapper design often matters more than just swapping the underlying model.
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