AI BENCHY
Advertise here
#112

Qwen3.6 35B A3B

Qwen Release: 2026-04-20 Tested on: 2026-04-27 23:05 qwen/qwen3.6-35b-a3b::none
(medium) (none)

Summary

Qwen3.6 35B A3B scores 5.1 on AI BENCHY and ranks #112. It has 10.0 reliability, a 39.6% pass rate, $0.019 total cost, and 2.87s average response time.

What makes Qwen3.6 35B A3B unique: It stands out most in Coding, where it ranks #1, while Combined is its weakest area at #14.

Score

5.1

Consistency

7.4

Reliability

10.0

Total Cost (Current Price)

$0.019

Total Output Tokens

17,503

Total Input Tokens

0

Input Price

$0.162 / 1M

Output Price

$0.966 / 1M

Tests Correct

Wrong Tests: 12

Attempt pass rate: 39.6%

Flaky tests

5

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

Response Time (avg)

2.87s

Response Time (max): 12.46s

Response Time (total): 46.00s

Wrong answer: 10 Did not follow instructions: 2

Generation showcase

Hamster playing table tennis

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

#112 Qwen3.6 35B A3B

none
Cost
$0.008
Time
30.1s
Tokens
6,317 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:19 New test added 4.6 10.0 $0.031 ↑ Compare
2026-05-21 23:54 Suite changed 4.9 10.0 $0.030 Compare
2026-04-27 23:05 Initial run 5.1 10.0 $0.019 Current run

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

Qwen3.6 35B A3BnonevsMiMo-V2.5-PrononeQwen3.6 35B A3BnonevsGPT-5.4noneQwen3.6 35B A3BnonevsGLM 4.7 FlashnoneQwen3.6 35B A3Bnonevsgpt-oss-120bnoneFree AvailableQwen3.6 35B A3BnonevsGrok 4.20noneQwen3.6 35B A3BnonevsGemini 3 Flash PreviewmediumQwen3.6 35B A3BnonevsGemini 3.5 FlashhighQwen3.6 35B A3BnonevsNemotron 3 Ultra 550b A55bmediumFree AvailableQwen3.6 35B A3BnonevsGemini 3.5 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.6 7.6
Coding 10.0 10.0
Combined 0.0 0.0
Data parsing and extraction 10.0 10.0
Domain specific 3.5 4.4
General Intelligence 4.4 3.0
Instructions following 6.2 5.8
Puzzle Solving 3.2 9.9
Tool Calling 0.0 0.0

Compared models