List your company

Theorem Proving on CLEVER (examples)

5Solved Tests (Correct Entries)Numina Lean Agent
-0.21.152.53.85May 22, 2026

Evaluation results

MethodLinks
Numina Lean AgentBenchmark variant=P2026.0551
Claude Code + lean4-skillsBenchmark variant=P2026.0551
AristotleBenchmark variant=PM2026.055—
Kimina-ProverBenchmark variant=P2026.054—
GrindBenchmark variant=PU2026.052—
LeanHammerBenchmark variant=PU2026.051—
AesopBenchmark variant=PU2026.051—
CanonicalBenchmark variant=PU2026.050—