List your company

Theorem Proving on VERINA (advanced)

57Solved Tests (Correct)Numina Lean Agent
-2.2813.1128.543.89May 22, 2026

Evaluation results

MethodLinks
Numina Lean AgentBenchmark variant=P2026.05573
AristotleBenchmark variant=PM2026.05432
Claude Code + lean4-skillsBenchmark variant=P2026.05402
Kimina-ProverBenchmark variant=P2026.053—
GrindBenchmark variant=PU2026.052—
LeanHammerBenchmark variant=PU2026.050—
AesopBenchmark variant=PU2026.050—
CanonicalBenchmark variant=PU2026.050—