List your company

Formal Theorem Proving on Number Theory

2.51PutnamBenchHilbert
0.08680.71591.3451.9741Apr 29, 2026

Evaluation results

MethodLinks
HilbertBackbone=Gemini 2.5 Pro, System=Agentic System2026.042.512.19
Goedel-Prover-V2-8BType=Open-source LLM2026.042.11.72
HilbertBackbone=Gemini 3.1 Pro, System=Agentic System2026.041.871.52
Goedel-Prover-V2-32BType=Open-source LLM2026.041.621.27
HilbertBackbone=GPT-5.3-Codex, System=Agentic System2026.041.21.07
DreamProverBackbone=Gemini 3.1 Pro, System=Lemma Learning System2026.041.150.64
DreamProverBackbone=Gemini 2.5 Pro, System=Lemma Learning System2026.041.130.54
Gemini 2.5 ProType=Proprietary LLM2026.040.960.61
DreamProverBackbone=GPT-5.3-Codex, System=Lemma Learning System2026.040.890.27
Gemini 3.1 ProType=Proprietary LLM2026.040.590.6
DeepSeek-Prover-V2-7BType=Open-source LLM2026.040.580.5
Claude 4.6 OpusType=Proprietary LLM2026.040.510.4
GPT-5.3-CodexType=Proprietary LLM2026.040.180.13