#112

Qwen3.5 Plus 2026-04-20

Qwen Release: 2026-04-20 Tested on: 2026-06-04 13:10 qwen/qwen3.5-plus-20260420::none

~397B total (~17B active)MoEClosedEstimated

(medium) (none)

Summary

Qwen3.5 Plus 2026-04-20 scores 5.7 on AI BENCHY and ranks #112. It has 10.0 reliability, a 41.3% pass rate, $0.032 total cost, and 4.39s average response time.

What makes Qwen3.5 Plus 2026-04-20 unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Estimated

Parameters: ~397B total (~17B active)
Architecture: MoE
Availability: Closed
License: -

Best estimate from public evidence; the vendor did not disclose every value. Estimate from the released 397B/A17B family architecture.

Parameter source Availability source

Score

5.7

Consistency

8.6

Reliability

10.0

Total Cost (Current Price)

$0.032 ↓ -23.7%

Tested at: $0.042

Total Output Tokens

11,145

Total Input Tokens

38,910

Input Price

$0.300 / 1M

Output Price

$1.800 / 1M

Tests Correct

Wrong Tests: 14

Attempt pass rate: 41.3%

Flaky tests

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

Response Time (avg)

4.39s

Response Time (max): 33.34s

Response Time (total): 92.26s

Wrong answer: 12 Did not follow instructions: 2

Hamster playing table tennis

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

#112 Qwen3.5 Plus 2026-04-20

none

Cost: $0.008
Time: 77.0s
Tokens: 4,369 tok

Run history

Tested on	Score	Reliability	Total Cost	Compare
2026-08-14 01:39 Re-test	6.1	10.0	$0.122 ↓	Compare
2026-07-16 21:27 New test added	6.1	10.0	$0.122 ↓	Compare
2026-06-04 13:10 New test added	5.7	10.0	$0.032 ↓	Current run
2026-05-21 23:47 Suite changed	5.8	9.9	$0.041	Compare
2026-05-08 13:10 Suite changed	5.9	9.9	$0.040	Compare
2026-05-08 13:10 Suite changed	5.9	9.9	$0.040	Compare
2026-04-27 23:05 Initial run	5.8	9.8	$0.024	Compare

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

Run comparison

Run	Benchmark coverage	Score	Consistency	Reliability	Tests Correct	Flaky tests	Total Output Tokens	Total Input Tokens	Total Cost	Response Time (avg)
2026-06-04 13:10 · New test added	63/63 attempts	5.7	8.6	10.0	7/21	4	11,145	38,910	$0.032	4.39s
2026-07-16 21:27 · New test added	66/66 attempts	6.1	8.7	10.0	8/22	4	51,487	94,468	$0.122	13.56s
Difference	—	-0.4	-0.1	0.0	-1	0	-40342	-55558	-$0.090	-9166ms

Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date	Input Price	Output Price
2026-06-04 14:42	$0.300 / 1M	$1.800 / 1M

Charts

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

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category	Score	Consistency
Anti-AI Tricks	4.8	10.0
Coding	3.9	7.8
Combined	2.8	1.6
Data parsing and extraction	10.0	10.0
Domain specific	5.3	10.0
General Intelligence	4.8	10.0
Instructions following	6.2	5.8
Puzzle Solving	6.7	7.9
Tool Calling	10.0	10.0
Trivia	3.0	10.0

Qwen3.5 Plus 2026-04-20

Model facts

Hamster playing table tennis

#112 Qwen3.5 Plus 2026-04-20

Charts

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Compared models