{"slug":"kimi-k2-5","name":"Kimi K2.5","domain":"kimi.com","verdict":"As of 2026-07-15, ChatGPT, Claude, Gemini, Grok collectively rank Kimi K2.5 #6 of 13 for open-weight llm. Source: https://modelsagree.com/product/kimi-k2-5 (modelsagree.com, CC BY 4.0).","best_rank":6,"categories":1,"entries":[{"slug":"best-open-weight-llm","title":"Best open-weight LLM","rank":6,"of":13,"score":4,"appearances":1,"modelRanks":{"Grok":2},"reason":"Native multimodal agentic capabilities with strong vision+coding, agent swarms, and frontier-competitive benchmarks (high SWE-Bench Verified, GPQA); efficient MoE (1T total/32B active); open weights under Modified MIT for flexible app integration.","reasons":[{"model":"Grok","reason":"Native multimodal agentic capabilities with strong vision+coding, agent swarms, and frontier-competitive benchmarks (high SWE-Bench Verified, GPQA); efficient MoE (1T total/32B active); open weights under Modified MIT for flexible app integration."}],"fixes":[{"model":"Grok","fix":"Newer multimodal focus may require more tuning for pure text-only pipelines; inference scale still substantial."}],"updated":"2026-07-15","api":"https://modelsagree.com/api/v1/best/best-open-weight-llm.json"}],"page":"https://modelsagree.com/product/kimi-k2-5","check":"https://modelsagree.com/check?q=Kimi%20K2.5","updated":"2026-08-10T18:18:45.051Z","attribution":"modelsagree.com, CC BY 4.0"}