Paper: A UNIVERSITY-LEVEL BENCHMARK FOR EVALUATING MATHEMATICAL SKILLS IN LLMS
Toloka
company
Verified
AI & ML interests
Human-expert data for frontier reasoning, safety and agentic AI
Recent Activity
Organization Card
Hey, this is Toloka!
datasets
12
toloka/mu-math
Viewer
•
Updated
•
1.08k
•
33
•
24
toloka/u-math
Viewer
•
Updated
•
1.1k
•
363
•
26
toloka/vist
Viewer
•
Updated
•
39.3k
•
16
toloka/VOX-DUB
Viewer
•
Updated
•
7.58k
•
100
•
10
toloka/JEEM
Viewer
•
Updated
•
2.2k
•
87
•
14
toloka/beemo
Viewer
•
Updated
•
2.19k
•
422
•
19
toloka/CLESC
Viewer
•
Updated
•
500
•
12
•
2
toloka/VoxDIY-RusNews
Updated
•
50
•
3
toloka/CrowdSpeech
Updated
•
86
•
5
toloka/crowdkit-datasets
Updated
•
586