Theorem Proving on 567NEQ
57Solved ProblemsDreamProver
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 3.1 Pro2026.04 | 57 | 62 | — | |
| DreamProverMethod Category=Lemma Learning System, Backbone=GPT-5.3-Codex2026.04 | 55 | 59.8 | — | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 3.1 Pro2026.04 | 51 | 55.4 | — | |
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 2.5 Pro2026.04 | 49 | 53.3 | — | |
| HilbertMethod Category=Agentic System, Backbone=GPT-5.3-Codex2026.04 | 47 | 51.1 | — | |
| Gemini 3.1 ProMethod Category=Proprietary LLMs2026.04 | 44 | 47.8 | — | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 2.5 Pro2026.04 | 36 | 39.1 | — | |
| Goedel-Prover-V2-32BMethod Category=Open-source LLMs2026.04 | 25 | 27.2 | — | |
| GPT-5.3-CodexMethod Category=Proprietary LLMs2026.04 | 21 | 22.8 | — | |
| Claude 4.6 OpusMethod Category=Proprietary LLMs2026.04 | 14 | 15.2 | — | |
| Goedel-Prover-V2-8BMethod Category=Open-source LLMs2026.04 | 9 | 9.8 | — | |
| DeepSeek-Prover-V2-7BMethod Category=Open-source LLMs2026.04 | 7 | 7.6 | — | |
| Gemini 2.5 ProMethod Category=Proprietary LLMs2026.04 | 3 | 3.3 | — | |
| Claude 4.6 OpusType=Proprietary LLM2026.04 | — | — | 15.8 | |
| DeepSeek-Prover-V2-7BType=Open-source LLM2026.04 | — | — | 10.1 | |
| DreamProverBackbone=GPT-5.3-Codex, Type=Lemma Learning System2026.04 | — | — | 65.2 | |
| DreamProverBackbone=Gemini 2.5 Pro, Type=Lemma Learning System2026.04 | — | — | 43.8 | |
| DreamProverBackbone=Gemini 3.1 Pro, Type=Lemma Learning System2026.04 | — | — | 60.3 | |
| Gemini 2.5 ProType=Proprietary LLM2026.04 | — | — | 22.3 | |
| Gemini 3.1 ProType=Proprietary LLM2026.04 | — | — | 40.9 | |
| Goedel-Prover-V2-32BType=Open-source LLM2026.04 | — | — | 64.4 | |
| Goedel-Prover-V2-8BType=Open-source LLM2026.04 | — | — | 24.1 | |
| GPT-5.3-CodexType=Proprietary LLM2026.04 | — | — | 56.6 | |
| HilbertBackbone=GPT-5.3-Codex, Type=Agentic System2026.04 | — | — | 118.6 | |
| HilbertBackbone=Gemini 2.5 Pro, Type=Agentic System2026.04 | — | — | 97.1 | |
| HilbertBackbone=Gemini 3.1 Pro, Type=Agentic System2026.04 | — | — | 85.8 |