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

Theorem Proving on ProofNet (test)

47.3Pass@32

LongCat-Flash-Prover

Updated 25d ago

Evaluation Results

Method	Links
LongCat-Flash-Prover 2026.03		47.3	-	-	-	-	-
LongCat-Flash-Prover 2026.03		36.1	-	-	-	-	-
Claude-Opus-4.5 2026.03		35	-	-	-	-	-
DeepSeek-Prover-V2-671B 2026.03		30.5	-	-	-	-	-
Leanabell-Prover-V2-DS 2026.03		23.7	-	-	-	-	-
DeepSeek-Prover-V2-7B 2026.03		23	-	-	-	-	-
Gemini-3 Pro 2026.03		22	-	-	-	-	-
Goedel-Prover-V2-32B 2026.03		22	-	-	-	-	-
DeepSeek-V3.2 2026.03		20.4	-	-	-	-	-
Kimi-K2.5 2026.03		19.9	-	-	-	-	-
LongCat-Flash-Prover 2026.03		19.9	-	-	-	-	-
Kimina-Prover-72B 2026.03		18.3	-	-	-	-	-
Goedel-Prover-V2-8B 2026.03		16.7	-	-	-	-	-
Leanabell-Prover-V2-KM 2026.03		13.4	-	-	-	-	-
Kimina-Prover-8B 2026.03		11.8	-	-	-	-	-
Baseline 2025.04		-	9.6	-	-	-	-
Hierarchical Attention 2025.04		-	11.3	-	-	-	-
Baseline 2025.04		-	10.17	2	-	-	-
Hierarchical Attention 2025.04		-	12.8	2	1	31.25	-
Baseline 2025.04		-	13.56	2.4	-	-	-
Hierarchical Attention 2025.04		-	14.12	1.8	0.75	21.74	-
Baseline 2025.04		-	11.86	-	-	-	-
HAGBP 2025.04		-	11.86	-	-	-	-
Baseline 2025.04		-	13.56	1.83	-	-	-
HAGBP 2025.04		-	14.69	1.83	1	28.57	-
Baseline 2025.04		-	13.56	2	-	-	-
HAGBP 2025.04		-	15.25	1.67	0.84	26.09	-
DeepSeek-Prover-V2-671B 2026.03		-	-	-	-	-	37.1
Self-play Theorem Proving 2026.03		-	-	-	-	-	26.9
Leanabell-Prover-V2-KM 2026.03		-	-	-	-	-	18.2
Leanabell-Prover-V2-DS 2026.03		-	-	-	-	-	25.2
LongCat-Flash-Prover 2026.03		-	-	-	-	-	51.1
LongCat-Flash-Prover 2026.03		-	-	-	-	-	52.2