modelgrep
X

Xiaomi: MiMo-V2.5-Pro

xiaomi/mimo-v2.5-pro

8th smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
53.8
8th of 178
Design Elo
1334
3D
Speed
38
207th fastest
Latency
255ms
first token
Input price
$0.435
157th cheapest
Context
1.0M
131K max out

How it compares

Smarter than96%
of all ranked models
Faster than30%
of all ranked models
Cheaper than47%
of all ranked models

Overview

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....

Benchmarks

independent · via OpenRouter
Artificial Analysis96th percentile
Intelligence Index
53.8
Coding Index
45.5
Agentic Index
67.4
GPQA Diamond
87%
Humanity's Last Exam
34%
SciCode
50%
Tau²-Bench (agentic)
94%
Design Arena · Elo2,172 tournaments
3D
1334
Game Dev
1329
codecategories
1321
Website
1312
UI Component
1304
Data Viz
1298

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
Xiaomifp8$0.435$0.87099.8%
Novita$0.522$1.04100%
DeepInfrafp8$1.00$3.0094.9%

Specifications

Context window1.0M
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.0036/M
ModeratedNo

MiMo-V2.5-Pro FAQ

How much does MiMo-V2.5-Pro cost?

MiMo-V2.5-Pro costs $0.435 per million input tokens and $0.870 per million output tokens via OpenRouter, making it 157th cheapest of 298 paid models.

How smart is MiMo-V2.5-Pro?

MiMo-V2.5-Pro scores 53.8 on the Artificial Analysis Intelligence Index, ranking 8th of 178 benchmarked models, with a GPQA Diamond score of 87%.

How fast is MiMo-V2.5-Pro?

MiMo-V2.5-Pro generates around 38 tokens per second with 255ms time-to-first-token (p50), the 207th fastest tracked model.

What is MiMo-V2.5-Pro's context window?

MiMo-V2.5-Pro supports a 1.0M-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head