#43

Qwen3.5 Plus 2026-04-20

Qwen Release: 2026-04-20 Tested on: 2026-05-21 23:53 qwen/qwen3.5-plus-20260420::medium

~397B total (~17B active)MoEClosedEstimated

(medium) (none)

Summary

Qwen3.5 Plus 2026-04-20 scores 7.6 on AI BENCHY and ranks #43. It has 9.6 reliability, a 71.7% pass rate, $0.363 total cost, and 43.63s average response time.

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

7.6

Consistency

8.7

Reliability

9.6

Total Cost (Current Price)

$0.363

Total Output Tokens

152,480

Total Input Tokens

Input Price

$0.300 / 1M

Output Price

$1.800 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 71.7%

Flaky tests

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

Response Time (avg)

43.63s

Response Time (max): 189.38s

Response Time (total): 872.61s

Wrong answer: 7

Hamster playing table tennis

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

#43 Qwen3.5 Plus 2026-04-20

medium

Cost: $0.008
Time: 76.7s
Tokens: 4,355 tok

Run history

Tested on	Score	Reliability	Total Cost	Compare
2026-08-14 01:42 Re-test	7.2	9.6	$0.323 ↓	Compare
2026-07-16 22:06 New test added	7.2	9.6	$0.317 ↓	Compare
2026-06-04 13:15 New test added	7.6	9.9	$0.317 ↓	Compare
2026-05-21 23:53 Suite changed	7.6	9.6	$0.363	Current run
2026-05-08 14:34 Suite changed	7.8	9.6	$0.305	Compare
2026-05-08 14:34 Suite changed	7.8	9.6	$0.305	Compare
2026-04-27 23:09 Initial run	8.2	9.7	$0.269	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)
2026-05-21 23:53 · Suite changed	60/60 attempts	7.6	8.7	9.6	13/20	3	152,480	0	$0.363	43.63s
2026-07-16 22:06 · New test added	66/66 attempts	7.2	9.0	9.6	13/22	2	168,893	42,097	$0.317	46.36s
Difference	—	+0.4	-0.3	0.0	0	+1	-16413	-42097	+$0.046	-2730ms

Benchmark coverage differs: 60/60 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.

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	10.0	10.0
Coding	5.4	6.0
Combined	10.0	10.0
Data parsing and extraction	10.0	10.0
Domain specific	2.9	7.2
General Intelligence	4.9	9.6
Instructions following	10.0	10.0
Puzzle Solving	8.2	7.2
Tool Calling	10.0	10.0
Trivia	3.0	10.0

Qwen3.5 Plus 2026-04-20

Model facts

Hamster playing table tennis

#43 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