Unverified50% confidenceBenchmarkExact time
VisKG-LM achieves improvements of 1.2, 0.8, and 4.3 points over the GreaseLM baseline on the three benchmarks CommonsenseQA, OpenBookQA, and MedQA-USMLE, respectively.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMeta's Llama 3.1 supports 405B parameters, and open-source models including Qwen2.5 and DeepSeek-V3 have approached or even surpassed some closed-source commercial models on multiple benchmarks.62% similarUnverifiedLlama 3.1 405B's score on MMLU is already close to the level of GPT-4o, and Qwen 2.5 72B has surpassed GPT-4 Turbo on certain metrics in math and code generation benchmarks.62% similarUnverifiedHY3 still lags behind GLM 5.2 (the current top-level open-source model) in overall performance.62% similarUnverifiedLFM2.5 improved by 19 and 23 points respectively over the previous generation in the BFCL-v3 and BFCL-v4 tool-calling evaluations.62% similarUnverifiedThe Zhipu GLM series continuously refined three generations at the 358B parameter scale from GLM4.5 to 4.7, after which GLM5 doubled to 754B.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931211API
curl https://kongchang.com/api/v1/knowledge/claims/931211MCP
get_claim(id=931211)