TRACES: New Benchmark Evaluates AI on Open-Ended Problems

Apodex introduced TRACES, a benchmark that evaluates AI systems—rather than single models—on real open-ended problems with unknown answers across six capabilities, achieving a 7% improvement over SOTA on AAV capsid design.

2026-09-24 ~ 2026-09-24 · 2 related posts

• TRACES: A New Benchmark That Grades AI Problem-Solving Process, Not Just Correct Answers — dr_cintas · 2026-09-24
• TRACES Benchmark Evaluates AI Beyond Final Answers, Beats SOTA by 7% on AAV Capsid Design — dr_cintas · 2026-09-24