modelgrep
Q

Qwen: Qwen3 Max

qwen/qwen3-max

91st smartest of 180ToolsJSON
Use via OpenRouter ↗
Intelligence
26.1
91st of 180
Design Elo
1172
asciiart
Speed
25
260th fastest
Latency
1.1s
first token
Input price
$0.780
191st cheapest
Context
262K
33K max out

How it compares

Smarter than49%
of all ranked models
Faster than15%
of all ranked models
Cheaper than36%
of all ranked models

Overview

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

Benchmarks

independent · via OpenRouter
Artificial Analysis45th percentile
Intelligence Index
26.1
Coding Index
25.5
Agentic Index
23.3
GPQA Diamond
76%
Humanity's Last Exam
9%
SciCode
37%
Tau²-Bench (agentic)
33%
Design Arena · Elo16,352 tournaments
asciiart
1172
Game Dev
1164
Website
1163
codecategories
1161
3D
1155
Data Viz
1149
UI Component
1134
svg
1068

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Alibabacache$0.780$3.90100%

Specifications

Context window262K
Max output33K
Knowledge cutoffJun 2025
Input modalitiestext
Output modalitiestext
Prompt cachingSupported
Cache read price$0.156/M
ModeratedNo

Qwen3 Max FAQ

How much does Qwen3 Max cost?

Qwen3 Max costs $0.780 per million input tokens and $3.90 per million output tokens via OpenRouter, making it 191st cheapest of 298 paid models.

How smart is Qwen3 Max?

Qwen3 Max scores 26.1 on the Artificial Analysis Intelligence Index, ranking 91st of 180 benchmarked models, with a GPQA Diamond score of 76%.

How fast is Qwen3 Max?

Qwen3 Max generates around 25 tokens per second with 1.1s time-to-first-token (p50), the 260th fastest tracked model.

What is Qwen3 Max's context window?

Qwen3 Max supports a 262K-token context window and can output up to 33K tokens. It accepts text input.

Compare head-to-head