Xiaomi: MiMo-V2.5-Pro

Text input Text output
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:

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

This model supports the following features:

Tools Reasoning Response Format
Performance Summary

MiMo-V2.5-Pro, Xiaomi’s flagship model, demonstrates exceptional reliability with a 100% success rate across all benchmarks, consistently providing usable responses. While it tends to have longer response times, ranking in the 17th percentile for speed, and is positioned at premium pricing levels (12th percentile), its performance in critical areas is robust. The model excels in General Knowledge and Ethics, achieving perfect 100% accuracy in both, and stands out as the most accurate model at its price point and speed in these categories. It also shows strong capabilities in Coding (96% accuracy, 96th percentile) and Reasoning (96% accuracy, 80th percentile). Instruction Following is a notable strength at 77% accuracy (82nd percentile). Hallucination rates are commendably low at 98% accuracy, indicating a strong ability to acknowledge uncertainty. Email Classification, while solid at 98% accuracy, is a more average performance compared to its other strengths. Overall, MiMo-V2.5-Pro is a highly reliable model with significant strengths in knowledge, ethical reasoning, and complex problem-solving, albeit at a premium cost and with longer processing times.

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
DeepInfra
DeepInfra | 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