---
title: "MiMo V2.5 Pro Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for MiMo V2.5 Pro."
source: "https://rankedagi.com/models/mimo-v2-5-pro"
---

# MiMo V2.5 Pro

| Field | Value |
| --- | --- |
| Organization | Xiaomi |
| License | Open Source |
| Version | Latest |
| Released | 2026-04-22 |
| Last updated | 2026-05-28T08:57:27.471Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 79.0% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 57.2% | Diverse Agentic Coding |  |
| Terminal-Bench 2.0 | coding | 68.4% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 77.1% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1471 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| DeepSWE | coding | 19.0% | Measuring frontier coding agents on original, long-horizon engineering tasks | https://deepswe.datacurve.ai/ |
| RankedAGI Reasoning | reasoning | 72.2% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 34.0% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 48.0% | Multidisciplinary Reasoning (with tools) |  |
| Text Arena | general | 1463 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| RankedAGI Math | math | 71.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 68.3% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1581 | Office Tasks (Artificial Analysis) |  |
| Tau3 Bench | Agents | 72.9% |  | https://sierra.ai/resources/research/tau-3-bench |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://mimo.xiaomi.com/mimo-v2-5-pro/ |