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

# MiMo V2.5

| Field | Value |
| --- | --- |
| Organization | Xiaomi |
| License | Open Source |
| Type | Thinking |
| Version | Latest |
| Released | 2026-04-22 |
| Last updated | 2026-05-04T01:02:19.399Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 74.3% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 56.1% | Diverse Agentic Coding |  |
| Terminal-Bench 2.0 | coding | 65.8% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 74.1% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1444 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| RankedAGI Reasoning | reasoning | 69.5% | RankedAGI Reasoning Score |  |
| Text Arena | general | 1424 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| RankedAGI Math | math | 64.6% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 65.6% | Overall RankedAGI score |  |
| Tau3 Bench | Agents | 69.5% |  | https://sierra.ai/resources/research/tau-3-bench |

## Model Links

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