AI4AI-Bench
Explore score history ↗AI4AI-Bench evaluates LLM agents on algorithmic design across 10 frozen research repositories. Agents rewrite training algorithms within 4 hours, then scored by fixed evaluators against baseline algorithms, with submissions released for repeatable measurement.
- Released
- 2026-08-20
- Institutions
- Tsinghua University
- Evaluates
- Language & Knowledge, Self-Evolution, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
AI4AI-Bench paper
No reported scores are on record for this benchmark yet.