science-last-exam
science-last-exam is Dataset with 113 rows (Text). Explore, preview and download it on Hugging Face.. It is ranked #105 on the AI Radar, in AI agents, first seen 20 h ago and shared in 6 posts (41.2k views).
Gen-Verse/Science-Last-Exam · Datasets at Hugging Face Hugging Face Log In Sign Up Datasets: Gen-Verse / Science-Last-Exam Like 0 Follow Gen-Verse 165 Modalities: Text Formats: parquet Languages: English Chinese Size: < 1K Tags: science agent-benchmark benchmark evaluation Libraries: Datasets pandas Polars + 1 License: cc-by-4.0 Dataset card Data Studio Files Files and versions xet Community 1 str:\n \"\"\"Centrifuge a sample at a defined speed, duration, and temperature.\n \n Args:\n sample: Sample or tube placed in the centrifuge.\n speed_xg: Relative centrifugal force in x g.\n duration_min: Spin time in minutes.\n temperature_c:…
What people said about science-last-exam on X
Can AI agents do scientific research on their own? Science's Last Exam is a new benchmark measure this. It's built from real research tasks across nine scientific fields. It tests whether an agent can form hypotheses, plan protocols, run scientific code and software, and read what happens in experiment videos.…
— @omarsar0, 20 h ago · 133 likes · see the post
Another new eval, another expected result Here at least V4.1F is closer to Kimi than to the trash tier. But the gap even to Opus 5 (which is, surprisingly, above Sol) is depressive.
— @teortaxesTex, 6 h ago · 45 likes · see the post
Here we go! Science's last exam. A benchmark for scientific research: statistics, physics, astronomy, chemistry, earth science, biology, engineering, materials science, and... medicine! Models are scored on 5 domains: hypothesis discovery, protocol planning, scientific computing, software operation and experiment…
— @DrSamuelBHume, 19 h ago · 30 likes · see the post
Alternatives to science-last-exam
- Z.ai — chief scientist Jie Tang just revealed the training pipeline behind the upcoming GLM-5.5 (32B, 122B, and 256B) during…
- Firecrawl — @firecrawl - Give your AI agents web data and beyond
- dsh-superagent-prototype — DeepSeek open-sourced the design behind its always-on 'Super-agent': no chat window, and reportedly nearly half the…
- REA for Growth — 4,000+ data endpoints, one key.
- Muse — We've now paid out more than $1M in @muse bug bounties. That includes $300,000 to a security researcher who found the…
- Console by Nace.AI — Cloud Inference
science-last-exam in numbers
- Rank on the AI Radar: #105 of 10392
- Shared in 6 posts by 6 accounts: @omarsar0, @teortaxesTex, @DrSamuelBHume, @rohanpaul_ai
- 41.2k views on those posts
- First seen 20 h ago, last shared 6 h ago
- Pricing seen by AGK Intelligence: free
- Market: AI agents
FAQ
What is science-last-exam?
Dataset with 113 rows (Text). Explore, preview and download it on Hugging Face. It was first shared on X 20 h ago and is ranked #105 on the AI Radar.
Is science-last-exam free?
Yes, it is free to use.
Who shared science-last-exam?
6 accounts on X, including @omarsar0, @teortaxesTex, @DrSamuelBHume, in 6 posts totalling 41.2k views.
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. 65.7k 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 13:40 UTC. Full method.