Theorem Proving on Synthetic
17Solved CountDreamProver (GPT-5.3-Codex)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DreamProver (GPT-5.3-Codex)Backbone LLM=GPT-5.3-Codex, Lemma Learning System=True, Pass@k=pass@322026.04 | 17 | 85 | |
| DreamProver (Gemini 3.1 Pro)Backbone LLM=Gemini 3.1 Pro, Lemma Learning System=True, Pass@k=pass@322026.04 | 17 | 85 | |
| DreamProver (Gemini 2.5 Pro)Backbone LLM=Gemini 2.5 Pro, Lemma Learning System=True, Pass@k=pass@322026.04 | 16 | 80 | |
| GPT-5.3-CodexBackbone LLM=GPT-5.3-Codex, Lemma Learning System=False, Pass@k=pass@322026.04 | 15 | 75 | |
| Gemini 3.1 ProBackbone LLM=Gemini 3.1 Pro, Lemma Learning System=False, Pass@k=pass@322026.04 | 13 | 65 | |
| Gemini 2.5 ProBackbone LLM=Gemini 2.5 Pro, Lemma Learning System=False, Pass@k=pass@322026.04 | 12 | 60 |