Science's Last Exam
AI & ML interests
LLM, Agents, RL
Recent Activity
Organization Card
Contact Us: Interested in learning more or getting involved? Reach out to us at ly1988@princeton.edu or visit our website at https://github.com/Gen-Verse.
models 25
Gen-Verse/DiscoveryRSI-27B
Text Generation • 28B • Updated • 383 • 12
Gen-Verse/RLAnything-Coder-7B
8B • Updated • 23 • 3
Gen-Verse/RLAnything-UT-14B
841k • Updated • 16 • 3
Gen-Verse/RLAnything-OS-8B
770k • Updated • 22 • 5
Gen-Verse/RLAnything-OS-Reward-8B
770k • Updated • 26 • 2
Gen-Verse/RLAnything-Alf-Reward-14B
15B • Updated • 19 • 3
Gen-Verse/RLAnything-Alf-7B
8B • Updated • 22 • 4
Gen-Verse/TraDo-8B-Thinking
8B • Updated • 141 • 15
Gen-Verse/TraDo-4B-Instruct
4B • Updated • 164 • 12
Gen-Verse/TraDo-8B-Instruct
8B • Updated • 249 • 13
datasets 35
Gen-Verse/Science-Last-Exam-reference
Updated • 128 • 4
Gen-Verse/Science-Last-Exam-data
Updated • 150 • 1
Gen-Verse/Science-Last-Exam
Viewer • Updated • 113 • 123 • 4
Gen-Verse/DiscoveryRSI-Hypothesis-Task-Examples
Viewer • Updated • 3 • 242 • 1
Gen-Verse/RSI-Anything
Viewer • Updated • 3.2k • 1.35k • 15
Gen-Verse/jepa-anything
Updated • 506 • 18
Gen-Verse/Skill2-Bench
Viewer • Updated • 300 • 108 • 6
Gen-Verse/perturb_ubuntu_osworld_file_cache
Updated • 1.02k
Gen-Verse/LiveCodeBench-ReasonFlux
Preview • Updated • 144 • 1
Gen-Verse/LiveBench-ReasonFlux
Viewer • Updated • 128 • 80 • 1