8
U Math Leaderboard
🥇
U-MATH and μ-MATH leaderboard
Vitaliy Polshkov
cogwheelhead
AI & ML interests
Data-centric AI methods; Experiment design, statistical learning and causal inference approaches for LLM / agentic evaluations; "Proper old-school" RL and meta-learning techniques for LLM training
Recent Activity
posted
an
update
15 days ago
Me and my team have performed an in-depth investigation comparing o1 to R1 (and other reasoning models)
Link: https://toloka.ai/blog/r1-is-not-on-par-with-o1-and-the-difference-is-qualitative-not-quantitative
It started with us evaluating them on our own university-math benchmarks: U-MATH for problem-solving and μ-MATH for judging solution correctness (see the HF leaderboard: https://huggingface.co/spaces/toloka/u-math-leaderboard)
tl;dr: R1 sure is amazing, but what we find is that it lags behind in novelty adaptation and reliability:
* performance drops when updating benchmarks with fresh unseen tasks (e.g. AIME 2024 -> 2025)
* R1-o1 gap widens when evaluating niche subdomains (e.g. university-specific math instead of the more common Olympiad-style contests)
* same with going into altogether unconventional domains (e.g. chess) or skills (e.g. judgment instead of problem-solving)
* R1 also runs into failure modes way more often (e.g. making illegal chess moves or falling into endless generation loops)
Our point here is not to bash on DeepSeek — they've done exceptional work, R1 is a game-changer, and we have no intention to downplay that. R1's release is a perfect opportunity to study where all these models differ and gain understanding on how to move forward from here
updated
a Space
19 days ago
toloka/u-math-leaderboard
liked
a Space
21 days ago
toloka/u-math-leaderboard
Organizations
cogwheelhead's activity
liked
a
Space
21 days ago
liked
2
datasets
3 months ago
liked
a
dataset
6 months ago