MiMo-V2.5-Pro is the best Xiaomi model for coding, with a 45.5 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. MiMo-V2.5 (42.1) and MiMo-V2-Flash (25.8) round out the top three.
AI models ranked by the Artificial Analysis Coding Index, measuring real-world software engineering ability across benchmarks like SWE-bench, SciCode and terminal tasks. The best LLMs for code generation, debugging and agentic development.
MiMo-V2.5-Pro is the best Xiaomi model for coding, with a 45.5 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. MiMo-V2.5 (42.1) and MiMo-V2-Flash (25.8) round out the top three.
MiMo-V2.5 (42.1) is the closest alternative on this metric, followed by MiMo-V2-Flash (25.8). See the full ranking above for the tradeoffs.
modelgrep tracks 3 Xiaomi models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by MiMo-V2.5-Pro. 3 of them qualify for this ranking.