xiaomi/mimo-v2.5-proMiMo-V2.5-Pro is Xiaomi Corp’s open-weights AI model, released Apr 23, 2026. It scores 149 on the Epoch Capabilities Index, costs $0.43/M input and $0.87/M output tokens, and handles a 1M-token context window. Its strongest use case is agentic & tools, where it ranks in the 71st percentile of the models Model Beat tracks.
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro…
Scores on standardized evaluations. Higher is better — and rank shows where MiMo-V2.5-Pro lands among all models tracked on Model Beat.
Graduate-level scientific reasoning
Frontier of human expert knowledge
Scientific research coding
Human-rated web development
Tool-agent-user reliability
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro…
MiMo-V2.5-Pro is an AI model developed by Xiaomi Corp, released Apr 23, 2026.
MiMo-V2.5-Pro is served from $0.43 per million input tokens and $0.87 per million output tokens (cheapest credible provider on OpenRouter: Xiaomi).
MiMo-V2.5-Pro supports a context window of up to 1M tokens.
On standardized evaluations tracked by Epoch AI, MiMo-V2.5-Pro scores 94.2% on τ²-bench, 50.6% on SciCode, 35.7% on Humanity's Last Exam.
MiMo-V2.5-Pro is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Nov 12, 2026.