Arena Math
LMArena subcategory ranking models on user pairwise votes restricted to math-related prompts.
- Operator
- LMArena
- Kind
- Human preference
- Updates
- live
- Notable for
- The user-preference complement to math accuracy benchmarks like MATH, AIME, and FrontierMath.
- Tracks
- Preference voting (no benchmark)
Cite
Notes
Only stored in your browser.
Backing benchmark
Human-preference voting. No underlying benchmark - models are ranked by pairwise votes, not by a test you can run.