MiMo-V2.5-Pro Official Specifications, Pricing & Benchmarks
MiMo-V2.5-Pro (mimo-v2.5-pro) by Xiaomi 小米 MiMo, released 2026-04-22, featuring 262,144 context window, 235,929 max output tokens, and Text input.
📋 MiMo-V2.5-Pro Official API & System Card Specifications
Verified against official Xiaomi 小米 MiMo developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- mimo-v2.5-pro
- Release Date
- 2026-04-22
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 262,000 tokens (262K)
- Max Output Tokens
- 235,929 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- ✅ Direct CN + RMB
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.48
- Cached Input / 1M
- $ 0.096 -80%
- Output / 1M Tokens
- $ 1.8
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 MiMo-V2.5-Pro Full Benchmark Scorecard
28 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 6 items
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
MiMo Coding Bench evaluates coding-agent capabilities on software engineering tasks reported with the MiMo model family.
Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal.
Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
WildClawBench is an agentic coding benchmark from InternLM/Claw-Eval that reports overall model performance on real-world tool-using development tasks.
🤖 Agents & Tools 2 items
TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities, testing models on multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
📐 Math 8 items
Grade School Math 8K, a dataset of 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater.
DROP (Discrete Reasoning Over Paragraphs) is a reading comprehension benchmark requiring discrete reasoning over paragraph content.
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.
🧠 Reasoning & Science 11 items
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities.
C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context.
CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of large language models across 67 different subject topics.
A challenging commonsense natural language inference dataset that uses Adversarial Filtering to create questions trivial for humans (>95% accuracy) but difficult for state-of-the-art models, requiring completion of sentence endings based on physical situations and everyday…
WinoGrande: An Adversarial Winograd Schema Challenge at Scale. A large-scale dataset of 44,000 pronoun resolution problems designed to test machine commonsense reasoning.
A comprehensive multilingual benchmark covering 42 languages that addresses cultural and linguistic biases in evaluation, with improved translation quality and culturally sensitive question subsets.
A large-scale reading comprehension dataset containing over 650K question-answer-evidence triples.
Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code.
MBPP+ is an enhanced version of MBPP (Mostly Basic Python Problems) with significantly more test cases (35x) for more rigorous evaluation.
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to MiMo-V2.5-Pro
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is MiMo-V2.5-Pro open-source or proprietary?
MiMo-V2.5-Pro (mimo-v2.5-pro) is a proprietary commercial model by Xiaomi 小米 MiMo. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of MiMo-V2.5-Pro?
MiMo-V2.5-Pro supports 262K input context and 235,929 max output tokens, priced at $0.48/1M input ($0.096/1M cached) and $1.8/1M output.