Share your thoughts, 1 month free Claude Pro on usSee more

Theorem Autoformalization on FormalPhysics

100FV

FormalPhysics

Updated 1mo ago

Evaluation Results

Method	Links
FormalPhysics 2026.04		100	6.41	6.22	73.5	72	72.5
Kimina-7B 2026.04		51.5	-	-	11	14.5	6.5
Kimina-7B 2026.04		23	-	-	6	7.5	5
GPT-5.1 2026.04		17	-	-	38	35	42
GPT-5.1 2026.04		14.5	-	-	27	28	33
DeepSeek-Prover-7B 2026.04		13	-	-	12.5	13.5	14
GPT-OSS-20B 2026.04		7.5	-	-	14.5	10.5	16.5
GPT-OSS-20B 2026.04		4.5	-	-	15.5	12.5	17.5
DeepSeek-Prover-7B 2026.04		4.5	-	-	26.5	11.5	17
Qwen2.5-Coder-7B 2026.04		1	-	-	8	9	12.5
Qwen2.5-Coder-7B 2026.04		1	-	-	11.5	7	10.5