Unverified50% confidenceBenchmarkExact time
On the MathlibQR benchmark, LeanGraphSearch improves recall by up to 12% relative to the strongest baseline, LeanSearch v2.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the FEVER benchmark, an 8B-scale backbone model paired with the R2VC architecture achieved an accuracy improvement of 13.74% over the baseline.58% similarUnverifiedDeepSeek的编程智能体DeepSWE在SWE-bench基准测试中从预览版的12.8分提升至62.7分56% similarUnverifiedvLLM v0.3.1 delivers deep optimizations for the DeepSeek series of models, with inference accelerated 1.9x in low-concurrency scenarios and throughput increased 5.3x in high-concurrency scenarios.55% similarUnverifiedDeepSeek Math V2 支持使用 Lean、Coq 等证明助手语言的形式化定理证明55% similarUnverifiedDeepSeek Coder以DeepSeek Math为底层基础，DeepSeek Math在MATH、GSM8K等数学基准上表现优异53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042030API
curl https://kongchang.com/api/v1/knowledge/claims/1042030MCP
get_claim(id=1042030)