Xiaomi: MiMo-V2.5-Pro

Text input Text output Unavailable
Author's Description

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....

Key Specifications
Cost
$$$$$
Context
1M
Released
Apr 22, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Include Reasoning Tools Response Format Temperature Max Tokens Reasoning Presence Penalty Stop Top P Frequency Penalty
Features

This model supports the following features:

Tools Reasoning Response Format
Performance Summary

Xiaomi's MiMo-V2.5-Pro demonstrates strong overall performance, particularly excelling in reliability with a perfect 100% success rate across all benchmarks, indicating exceptional stability. While its speed performance is moderate, ranking in the 23rd percentile, and its pricing is positioned at premium levels (13th percentile), the model delivers high accuracy across various critical tasks. It shows impressive capabilities in Instruction Following (82nd percentile accuracy) and Reasoning (81st percentile accuracy), aligning with its description as a strong performer in general agentic capabilities and complex software engineering. The model also exhibits a low hallucination rate (96.0% accuracy), effectively acknowledging uncertainty. Its performance in Email Classification is robust at 98.0% accuracy, and it maintains a high standard in Ethics with 99.0% accuracy. Key strengths include its outstanding reliability and high accuracy in complex cognitive tasks, while its primary weakness lies in its moderate speed and premium cost.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1
Completion $3
Input Cache Read $0.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Xiaomi
Xiaomi | xiaomi/mimo-v2.5-pro-20260422 1M $1 / 1M tokens $3 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by xiaomi