Apodex releases TRACES, the first benchmark for measuring 'discoverative AI' capabilities
aftahi_ai · x · 2026-08-23
Apodex has introduced TRACES, a new benchmark designed to evaluate 'discoverative intelligence'—the ability of AI to work through evidence, test hypotheses, and reach verifiable conclusions on problems without existing answer keys. Unlike benchmarks such as HLE or MMLU that measure retrieval of known answers, TRACES focuses on the process: using tools, fixing mistakes, and grounding conclusions. It has been applied to areas like rare-disease diagnosis, AAV gene delivery, and drug repurposing, asking whether a conclusion was actually earned rather than just guessed.
Related event: Apodex Launches TRACES Benchmark for AI Scientific Discovery(2 posts)→
More from Research
- Cohere Labs world model course session 4: DreamerV1-V4 architectures in one go — Cohere_Labs · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- One tiny word changes the conversation: how LLMs pick up on 'just' — StellaLisy · 2026-10-16
- SEAR: first large-scale controlled study of self-evolving robot agents, 7 LLMs, 330 tasks — xiye_nlp · 2026-10-16
- After Claude-assisted elliptic curve records fell, EC Rank challenge opens 156 record slots — Jsevillamol · 2026-10-16
- Oxford neuroscientist swaps fetal MRI for ultrasound + ML models — AnnaCiaunica · 2026-10-16