Theorem Proving on ChenNEQ
36Solved ProblemsDreamProver
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 3.1 Pro2026.04 | 36 | 85.7 | — | |
| Gemini 3.1 ProMethod Category=Proprietary LLMs2026.04 | 33 | 78.6 | — | |
| DreamProverMethod Category=Lemma Learning System, Backbone=GPT-5.3-Codex2026.04 | 33 | 78.6 | — | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 3.1 Pro2026.04 | 31 | 73.8 | — | |
| HilbertMethod Category=Agentic System, Backbone=GPT-5.3-Codex2026.04 | 30 | 71.4 | — | |
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 2.5 Pro2026.04 | 28 | 66.7 | — | |
| GPT-5.3-CodexMethod Category=Proprietary LLMs2026.04 | 27 | 64.3 | — | |
| Goedel-Prover-V2-32BMethod Category=Open-source LLMs2026.04 | 26 | 61.9 | — | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 2.5 Pro2026.04 | 23 | 54.8 | — | |
| Goedel-Prover-V2-8BMethod Category=Open-source LLMs2026.04 | 20 | 47.6 | — | |
| Claude 4.6 OpusMethod Category=Proprietary LLMs2026.04 | 19 | 45.2 | — | |
| DeepSeek-Prover-V2-7BMethod Category=Open-source LLMs2026.04 | 13 | 31 | — | |
| Gemini 2.5 ProMethod Category=Proprietary LLMs2026.04 | 5 | 11.9 | — | |
| Claude 4.6 OpusType=Proprietary LLM2026.04 | — | — | 15.2 | |
| DeepSeek-Prover-V2-7BType=Open-source LLM2026.04 | — | — | 14.5 | |
| DreamProverBackbone=GPT-5.3-Codex, Type=Lemma Learning System2026.04 | — | — | 57.6 | |
| DreamProverBackbone=Gemini 2.5 Pro, Type=Lemma Learning System2026.04 | — | — | 32.9 | |
| DreamProverBackbone=Gemini 3.1 Pro, Type=Lemma Learning System2026.04 | — | — | 37.8 | |
| Gemini 2.5 ProType=Proprietary LLM2026.04 | — | — | 25.9 | |
| Gemini 3.1 ProType=Proprietary LLM2026.04 | — | — | 29.7 | |
| Goedel-Prover-V2-32BType=Open-source LLM2026.04 | — | — | 63.3 | |
| Goedel-Prover-V2-8BType=Open-source LLM2026.04 | — | — | 21.8 | |
| GPT-5.3-CodexType=Proprietary LLM2026.04 | — | — | 46.6 | |
| HilbertBackbone=GPT-5.3-Codex, Type=Agentic System2026.04 | — | — | 113.4 | |
| HilbertBackbone=Gemini 2.5 Pro, Type=Agentic System2026.04 | — | — | 79.5 | |
| HilbertBackbone=Gemini 3.1 Pro, Type=Agentic System2026.04 | — | — | 87.9 |