AI BENCHY
Advertise here
#70

Qwen3.5-35B-A3B

Qwen Release: 2026-02-24 Tested on: 2026-05-22 00:15 qwen/qwen3.5-35b-a3b::medium
35B total (3B active)MoEOpen source
(medium) (none)

Summary

Qwen3.5-35B-A3B scores 7.0 on AI BENCHY and ranks #70. It has 6.7 reliability, a 71.7% pass rate, $0.547 total cost, and 69.43s average response time.

What makes Qwen3.5-35B-A3B unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-08-12

Reported
Parameters
35B total (3B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0
Parameter source Availability source

Score

7.0

Consistency

7.1

Reliability

6.7

Total Cost (Current Price)

$0.547

Total Output Tokens

367,406

Total Input Tokens

0

Input Price

$0.139 / 1M

Output Price

$1.000 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 71.7%

Flaky tests

7

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

Response Time (avg)

69.43s

Response Time (max): 409.98s

Response Time (total): 1388.55s

Timed out: 4 Wrong answer: 3 No answer: 2 API error: 1

Hamster playing table tennis

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

#70 Qwen3.5-35B-A3B

medium
Cost
$0.009
Time
71.4s
Tokens
8,631 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 01:57 Re-test 6.1 10.0 $1.623 ↑ Compare
2026-07-16 22:51 New test added 6.2 10.0 $0.837 ↓ Compare
2026-06-04 13:42 New test added 7.1 8.9 $0.401 ↓ Compare
2026-05-22 00:15 Suite changed 7.0 6.7 $0.547 Current run
2026-04-11 01:44 First recorded run 7.4 N/A $0.398 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

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

Qwen3.5-35B-A3BmediumvsGemini 3.1 Flash LiteminimalQwen3.5-35B-A3Bmediumvsgpt-oss-120bmediumQwen3.5-35B-A3BmediumvsClaude Sonnet 5noneQwen3.5-35B-A3BmediumvsQwen3.7 FlashnoneQwen3.5-35B-A3BmediumvsGPT-5.6 LunalowQwen3.5-35B-A3BmediumvsGemini 3.1 Flash LitenoneQwen3.5-35B-A3BmediumvsGemma 4 31BmediumFree AvailableQwen3.5-35B-A3BmediumvsQwen3.5-FlashmediumQwen3.5-35B-A3BmediumvsSeed-2.0-LitenoneQwen3.5-35B-A3BmediumvsInklinglow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 6.5 10.0
Combined 4.7 1.6
Data parsing and extraction 7.3 5.9
Domain specific 4.1 4.4
General Intelligence 2.8 1.6
Instructions following 10.0 10.0
Puzzle Solving 6.4 4.4
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models