Submissions from matharena.ai

		Creating Post-Training Datasets for Research-Level Mathematics (matharena.ai)
		3 points by frozenseven 13 days ago \| past \| discuss
		ArXivLean: How Well Can LLMs Formally Prove Research Math? (matharena.ai)
		3 points by OxfordCommand 4 months ago \| past
		BrokenArXiv: How often do LLMs claim to prove false theorems? (matharena.ai)
		3 points by robinhouston 5 months ago \| past
		MathArena: Evaluating LLMs on uncontaminated math questions (matharena.ai)
		2 points by GaggiX 6 months ago \| past
		New open source model achieves same score as GPT 5.2 High on AIME2026 I (matharena.ai)
		3 points by mh3467 7 months ago \| past \| 2 comments
		MathArena Apex: Unconquered Final-Answer Problems (matharena.ai)
		2 points by frozenseven 11 months ago \| past
		Evaluating publicly available LLMs on IMO 2025 (matharena.ai)
		79 points by hardmaru on July 19, 2025 \| past \| 89 comments
		Not Even Bronze: Evaluating LLMs on 2025 International Math Olympiad (matharena.ai)
		3 points by amichail on July 19, 2025 \| past \| 2 comments
		IMO 2025 LLM results are in (matharena.ai)
		5 points by arberavdullahu on July 18, 2025 \| past \| 1 comment
		Not Even Bronze? Evaluating LLMs on 2025 International Math Olympiad (matharena.ai)
		1 point by EvgeniyZh on July 18, 2025 \| past \| 1 comment
		Gemini 2.5 gets 24.4% on MathArena USAMO beating previous top score of 4.7% (matharena.ai)
		54 points by alphabetting on April 2, 2025 \| past \| 10 comments
		OpenAI o3-mini scores 78% on yesterday's AIME 2025 math competition (matharena.ai)
		3 points by bmislav on Feb 7, 2025 \| past