Benchmark
Lean-IMO-Bench
A Lean-based formal benchmark of International Mathematical Olympiad (IMO) problems, used to evaluate the performance of automated theorem proving systems on olympiad-level problems.
Timeline (last 90 days)
Oct 20
On benchmarks shared with published prover systems, Maestro solved 669/672 problems on PutnamBench, 59/60 on Lean-IMO-Bench, and achieved 6/6 on IMO 2026.
Unverified50%
Oct 20
Lean-IMO-Bench comes from formalized versions of International Mathematical Olympiad problems.
Unverified50%