Advertise here
#105

Qwen4 Max

Qwen Release: 2026-11-16 Tested on: 2026-11-16 06:13 qwen/qwen4-max::high
~2.4T total (~95B active)MoEClosedEstimated

Summary

Qwen4 Max scores 8.6 on AI BENCHY and ranks #105. It has 10.0 reliability, a 85.5% pass rate, $1.363 total cost, and 52.90s average response time.

What makes Qwen4 Max unique: It stands out most in Domain specific, where it ranks #2, while Agentic is its weakest area at #15.

Model facts

Researched on 2026-11-16

Estimated
Parameters
~2.4T total (~95B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Alibaba has not disclosed Qwen4 Max size. The estimate carries over the predecessor Qwen3.8-Max (2.4T total / 95B active MoE). No open weights were confirmed for the Max tier; OpenRouter serves it only through Alibaba Cloud with a 1M-token context and none/low/high/xhigh efforts. Fallback date records this onboarding request date.

Score

8.6

Consistency

9.6

Total Output Tokens

185,844

Total Input Tokens

350,854

Input Price

$1.500 / 1M

Output Price

$4.500 / 1M

Cache Read Price

$0.075 / 1M

Cache Write Price

$1.875 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 4

Attempt pass rate: 85.5%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

52.90s

Response Time (max): 437.98s

Response Time (total): 1216.62s

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#105 Qwen4 Max

high
Cost
$0.076
Time
277.5s
Tokens
16,848 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Agentic 5.0 10.0
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.9 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models