BREAKING: the best of 8 frontier models scored 37.5/100 on Science's Last Exam. On true…
This is a AI post classified by AGK Intelligence as AI research (a launch), kept by the AI Radar because it carries real work, not commentary.
BREAKING: the best of 8 frontier models scored 37.5/100 on Science's Last Exam. On true end-to-end research, all of them scored 0. AItonomy Foundation built 113 research tasks across 9 disciplines. Agents get live lab data and real software tools, then get graded against hidden expert checks. It opens Nov 6. Every "AI scientist" demo looks agentic for 45 seconds. A closed-loop grade is where it falls apart. So the moat for these products is not the model brand. It is the eval harness plus a domain expert seal on the results. If you build an AI scientist product, what hidden check would you
Posted by Guillermo Flor (14k followers) 10 h ago · 0 likes · 259 views · view the original post on X. Kept by the AI Radar as AI research.
More AI work like this
- No need for me to manually scan for new model releases anymore, since @paperswithcodee… — @NielsRogge
- We’re introducing ToyBlocks, an open simulated tabletop for controlled experiments in… — @allen_ai
- HotBench - Expert-authored tasks in medicinal chemistry, microbiology and dermatology to… — @SynBio1
- I wonder if you realize how interesting this is. — @SciTechera
- 🔥我靠！终于有大公司把AI模型后训练的“魔法”拆成可复现配方了！ — @NFT_Chen
- Stanford dropped a 2-hour course on building LLMs from scratch — @RoundtableSpace
- Meet DINOv3 ViT-H/16+: a powerful image feature extractor from the DINOv3 family. With… — @HuggingModels
- the self-reported uplift from Model 4 is insane — @scaling01
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.