MCPMark

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

20:47

2026-07-22

dev.to

artificial-intelligence

MCPMark v2: InsForge on Sonnet 4.6

InsForge MCP achieves 28% higher Pass⁴ accuracy while using 2.4x fewer tokens than Supabase MCP on Claude Sonnet 4.6, according to new MCPMark benchmarks. The efficiency gap has widened compared to So…

18:13

2026-06-14

dev.to

large-language-models

Kimi K2.7-Code: Open-Weight 1T Model That Beats Claude Opus on Tool Use

Moonshot AI released Kimi K2.7-Code, an open-weight 1 trillion parameter Mixture-of-Experts model that achieves 81.1% on MCPMark Verified, surpassing Claude Opus 4.8's 76.4% on tool-use tasks. The mod…

// co-occurs with top 8 entities

Moonshot AI 1 Kimi K2.7-Code 1 Claude Opus 4.8 1 GPT-5.5 1 Hugging Face 1 OpenRouter 1 The Decoder 1 InsForge 1

// topics top 6 topics

large language models 2 ai tools 1 ai products 1 ai infrastructure 1 ai research 1 artificial intelligence 1