Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Qwen

Qwen 2.5 Max

Qwen 2.5 Max is the upgraded version of Qwen Max, beating GPT-4o, Deepseek V3 and Claude 3.5 Sonnet in benchmarks.

Added Oct 1, 2024

Pricing

Auto routing · per 1M tokens
Input
$1.60
Output
$6.39
Compare provider prices

Specifications

Context window
32K
Max output
8.2K
Avg output (7d)
511 tokens
Longer than 42% of models

Benchmarks

Sourced from LMArena.

Arena Score

1373.7

Overall Rank

#200 / 421

Votes

32,484

Confidence Interval

1369.6 - 1377.9

Category Scores

Coding

#215 / 416

5,088 votes

1401.4

Math

#208 / 404

3,306 votes

1361.8

Longer Query

#191 / 399

4,534 votes

1384.8

Creative Writing

#179 / 419

5,011 votes

1353.2

Instruction Following

#206 / 421

10,958 votes

1356.3

Hard Prompts

#204 / 421

9,647 votes

1385.1

Additional Categories
22

French

#159 / 301

343 votes

1411.8

Japanese

#172 / 288

734 votes

1308.7

German

#182 / 320

781 votes

1354.4

Korean

#182 / 289

468 votes

1314.5

Spanish

#183 / 303

269 votes

1374.4

Polish

#184 / 244

850 votes

1358.3

Industry Writing And Literature And Language

#188 / 420

8,190 votes

1362.1

Industry Legal And Government

#192 / 393

1,857 votes

1387.7

Russian

#193 / 385

2,985 votes

1367.9

Industry Entertainment And Sports And Media

#194 / 419

5,985 votes

1339.6

Non English

#194 / 421

14,280 votes

1360.4

Industry Medicine And Healthcare

#195 / 390

1,594 votes

1394.2

Chinese

#197 / 395

2,073 votes

1396.9

Exclude Ties

#197 / 421

21,863 votes

1348.8

Industry Life And Physical And Social Science

#198 / 419

5,678 votes

1389.9

Multi Turn

#199 / 419

4,814 votes

1372.0

Industry Business And Management And Financial Operations

#200 / 414

3,660 votes

1368.4

English

#208 / 421

18,204 votes

1382.2

Industry Mathematical

#208 / 401

2,950 votes

1365.8

Expert

#214 / 371

1,684 votes

1367.2

Industry Software And It Services

#215 / 421

8,553 votes

1397.1

Hard Prompts English

#218 / 419

5,708 votes

1386.4

Published 2026-11-09 · Matched as Qwen2.5-Max

LMArena Dataset

Providers

Provider information for this model’s automatic routing. These routes cannot be selected individually.

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto
Recommended
$1.60$6.39N/AN/AN/A
Alibaba
Alibaba
SG
$1.60$6.39N/AN/AN/A
Privacy:No training on prompts

Related text models

Compare Qwen 2.5 Max with similar models from the same provider or model family.

Qwen3.8 Max Prime

qwen/qwen3.8-max-prime

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max for coding, complex analysis, and long-running agent workflows. It accepts text, image, and video input, supports tool calling and structured output, and has a 1M-token context window. Reasoning is always enabled.

Qwen 3.8 27B Antislop

qwen/qwen3.8-27b-antislop

Qwen 3.8 27B Antislop is a creative-writing finetune designed to reduce formulaic prose. Available capabilities include image understanding, tool calling, and optional reasoning, with context windows up to 262,144 tokens.

Qwen 3.8 27B DarkIdol

qwen/qwen3.8-27b-darkidol

Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Fimi

qwen/qwen3.8-27b-fimi

Qwen 3.8 27B Fimi is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Kimiko

qwen/qwen3.8-27b-kimiko

Qwen 3.8 27B Kimiko is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B Kiwen

qwen/qwen3.8-27b-kiwen

Qwen 3.8 27B Kiwen is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.