List your company

Automated Formal Theorem Proving on Putnam 2025

1,220Average ScoreHilbert
-48.282912280.982844610.2486939.514356Mar 25, 2026Apr 3, 2026Apr 12, 2026Apr 21, 2026Apr 30, 2026May 9, 2026May 19, 2026

Evaluation results

MethodLinks
HilbertMetric Category=Proof Length (#Lines)2026.031,220————————————1,220———
SeedMetric Category=Proof Length (#Lines)2026.031,161————6314699271,095—8818491,6135846282,4992,594
AxiomMetric Category=Proof Length (#Lines)2026.03763————5564581,0898251,8784681,1793463029931,310862
NuminaMetric Category=Proof Length (#Lines)2026.03667————3654014226053,2638353286902926489291,820
MechanicMetric Category=Proof Length (#Lines)2026.03656————112798560793—2801,4252246275681,256578
HilbertMetric Category=Time Expenditure (min)2026.03228————————————228———
SeedMetric Category=Time Expenditure (min)2026.03196————6030120240—24054036030120240180
AxiomMetric Category=Time Expenditure (min)2026.03187————1101801651075182592706543112254494
NuminaMetric Category=Time Expenditure (min)2026.03165————2781301692,04089551363030888797
MechanicMetric Category=Time Expenditure (min)2026.03114————2117910864—821324114812625893
NuminaMetric Category=Cost ($)2026.0372.7————505050501,000505050505050300
SeedMetric Category=Proof Tree Complexity (#Lemmas)2026.0349————27182328—3821482618103185
HilbertMetric Category=Proof Tree Complexity (#Lemmas)2026.0348————————————48———
HilbertMetric Category=Cost ($)2026.0337.9————————————37.9———
AxiomMetric Category=Proof Tree Complexity (#Lemmas)2026.0336————232678325228492811236630
MechanicMetric Category=Cost ($)2026.0318.5————4.212919.510.5—4.9129.83.7215.420.1579.01
NuminaMetric Category=Proof Tree Complexity (#Lemmas)2026.0317————15211177376149103341
MechanicMetric Category=Proof Tree Complexity (#Lemmas)2026.0314————120910—13029174510
STAR-PólyaMathBackbone=all GPT-5.5xh2026.051————————————————
GPT-5.5Reasoning Effort=xhigh2026.050.8958————————————————
Gemini 3.1 Pro2026.050.8854————————————————
GPT-5.4Reasoning Effort=xhigh2026.050.8333————————————————
Claude Opus 4.7Reasoning Effort=xhigh2026.050.7708————————————————
GPT-5.2Reasoning Effort=high2026.050.7604————————————————
Gemini 3 Pro2026.050.7583————————————————
Claude Opus 4.6Reasoning Effort=high2026.050.6458————————————————
DeepSeek-v3.2-Speciale2026.050.5917————————————————
Kimi K2.5Reasoning Effort=Think2026.050.4972————————————————