Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Formal Theorem Proving on UniGeo (10)
Loading...
4.1
Proof Length
GPT-5.3-Codex
3.972
4.836
5.7
6.564
Apr 29, 2026
Proof Length
Updated 1mo ago
Evaluation Results
Method
Method
Links
Proof Length
GPT-5.3-Codex
Method Category=Propri...
2026.04
4.1
Gemini 3.1 Pro
Method Category=Propri...
2026.04
5.2
Gemini 2.5 Pro
Method Category=Propri...
2026.04
5.6
DreamProver (Gemini 3.1 Pro)
Method Category=Lemma...
2026.04
6.2
DreamProver (GPT-5.3-Codex)
Method Category=Lemma...
2026.04
7
DreamProver (Gemini 2.5 Pro)
Method Category=Lemma...
2026.04
7.3
Feedback
Search any
task
Search any
task