---
title: "MiniMax M2.5 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for MiniMax M2.5."
source: "https://rankedagi.com/models/minimax-m2-5"
---

# MiniMax M2.5

| Field | Value |
| --- | --- |
| Organization | MiniMax |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-02-12 |
| Last updated | 2026-05-04T01:19:11.125Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 68.7% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 55.4% | Diverse Agentic Coding |  |
| SWEBench Multilingual | coding | 74.1% |  |  |
| SWEBench Verified | coding | 80.2% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 51.7% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 57.0% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1383 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 70.7% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 51.7% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| SvelteBench | coding | 95.6% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| RankedAGI Reasoning | reasoning | 60.4% | RankedAGI Reasoning Score |  |
| Vending Bench 2 | Agents | $-23.16 | Benchmark for measuring AI model performance on running a business over long time horizons. Models are tasked with running a simulated vending machine business over a year and scored on their bank account balance at the end. | https://andonlabs.com/evals/vending-bench-2 |
| RankedAGI Math | math | 69.7% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 59.0% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1186 | Office Tasks (Artificial Analysis) |  |
| Code DesignArena | Design | 1271 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 38.3% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.minimax.io/news/minimax-m25 |