Theorem Proving on UniGeo
10Solved CountGPT-5.3-Codex
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5.3-CodexBackbone LLM=GPT-5.3-Codex, Lemma Learning System=False, Pass@k=pass@322026.04 | 10 | 100 | |
| Gemini 2.5 ProBackbone LLM=Gemini 2.5 Pro, Lemma Learning System=False, Pass@k=pass@322026.04 | 10 | 100 | |
| Gemini 3.1 ProBackbone LLM=Gemini 3.1 Pro, Lemma Learning System=False, Pass@k=pass@322026.04 | 10 | 100 | |
| DreamProver (GPT-5.3-Codex)Backbone LLM=GPT-5.3-Codex, Lemma Learning System=True, Pass@k=pass@322026.04 | 10 | 100 | |
| DreamProver (Gemini 2.5 Pro)Backbone LLM=Gemini 2.5 Pro, Lemma Learning System=True, Pass@k=pass@322026.04 | 10 | 100 | |
| DreamProver (Gemini 3.1 Pro)Backbone LLM=Gemini 3.1 Pro, Lemma Learning System=True, Pass@k=pass@322026.04 | 10 | 100 |