Humanfia tops Lean-Eval with 166 problems solved on under 50k tokens via smart agent flow
YouJiacheng · x · 2026-08-18
The Humanfia team, powered by Humanize「2」, ranks #1 on the Lean-Eval leaderboard with 166 problems solved, 10 ahead of second place. Developer YouJiacheng notes they didn't brute-force tokens — total token cost stayed under 50k — by using a smart agent flow to drive the loop, and most team members aren't math majors, highlighting how much agent orchestration can leverage formal-proof benchmarks.
More from coding & agent
- Linux 7.2 ships AI-enriched scheduling as maintainer calls AI-assisted review "the new normal" — CackleRooster · 2026-08-18
- Study: AI Assistants Don't Close Gap Between Novice and Expert Devs — georgemillo · 2026-08-18
- Analysis of 23K AI-generated PRs: junior devs ship 2x more, 4x review load, 31% lower acceptance — georgemillo · 2026-08-18
- monday.com Rebuilds AI Copilot with Sandboxes and Subagents for Reliability — LangChain · 2026-08-18
- Qwen3.8 27B outscores GPT-5.6-Terra on Artificial Analysis Agentic Index — UnknownEssence · 2026-08-18
- How to Stop Agent Skills Sprawl to Save Tokens — rseroter · 2026-08-18