IMO-LeanProofBench
Not in model cards
Models write Lean 4 proofs for the 60 IMO-ProofBench problems, formalized by hand and checked by Lean experts. The Lean compiler verifies each proof.
Introduced with the LEAP paper. One-shot Gemini 3.1 Pro solved 11.6 percent and the LEAP agent 70 percent. The August 2026 v2 file fixed wrong formalizations for Mathlib 4.27.0.
Made by Google DeepMind (Superhuman Reasoning team) Released Jun 2026 Formal proofs All tasks public
- Level
- Competition The strongest students, in olympiad-style contests
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Written proof
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for IMO-LeanProofBench yet.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Math
- IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
- AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
- HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
- MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
- PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked.
Qwen3.7-Max 86.5% - USAMO 2026 In use Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. GPT-5.5 98.2%