Theorem Proving on CombiBench Combinatorics
27Solved ProblemsDreamProver
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 3.1 Pro2026.04 | 27 | 62.8 | |
| DreamProverMethod Category=Lemma Learning System, Backbone=GPT-5.3-Codex2026.04 | 26 | 60.5 | |
| DreamProverMethod Category=Lemma Learning System, Backbone=Gemini 2.5 Pro2026.04 | 25 | 58.1 | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 2.5 Pro2026.04 | 18 | 41.9 | |
| HilbertMethod Category=Agentic System, Backbone=GPT-5.3-Codex2026.04 | 17 | 39.5 | |
| HilbertMethod Category=Agentic System, Backbone=Gemini 3.1 Pro2026.04 | 17 | 39.5 | |
| Goedel-Prover-V2-32BMethod Category=Open-source LLMs2026.04 | 13 | 30.2 | |
| GPT-5.3-CodexMethod Category=Proprietary LLMs2026.04 | 12 | 27.9 | |
| Claude 4.6 OpusMethod Category=Proprietary LLMs2026.04 | 12 | 27.9 | |
| DeepSeek-Prover-V2-7BMethod Category=Open-source LLMs2026.04 | 8 | 18.6 | |
| Gemini 3.1 ProMethod Category=Proprietary LLMs2026.04 | 7 | 16.3 | |
| Goedel-Prover-V2-8BMethod Category=Open-source LLMs2026.04 | 7 | 16.3 | |
| Gemini 2.5 ProMethod Category=Proprietary LLMs2026.04 | 2 | 4.7 |