Advertise here
#365

Qwen3.5-9B

Qwen Release: 2026-03-02 Tested on: 2026-10-01 01:27 qwen/qwen3.5-9b::none
9BDenseOpen source
(medium) (none)

Summary

Qwen3.5-9B scores 4.9 on AI BENCHY and ranks #365. It has 9.8 reliability, a 18.8% pass rate, $0.041 total cost, and 37.19s average response time.

Model facts

Researched on 2026-08-12

Reported
Parameters
9B
Architecture
Dense
Availability
Open source
License
Apache-2.0
Parameter source Availability source

Score

4.9

Consistency

9.7

Reliability

9.8

Total Cost (Current Price)

$0.041

Total Output Tokens

70,427

Total Input Tokens

307,670

Input Price

$0.100 / 1M

Output Price

$0.150 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

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: 19

Attempt pass rate: 18.8%

Flaky tests

1

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

Response Time (avg)

37.19s

Response Time (max): 433.02s

Response Time (total): 855.27s

Wrong answer: 15 Did not follow instructions: 2 Invalid tool call: 2

Hamster playing table tennis

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

#365 Qwen3.5-9B

none
Reached the allocated time limit (300 seconds) without receiving showcase output.
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 01:27 Re-test 4.9 9.8 $0.041 Current run
2026-07-16 22:25 New test added 5.1 10.0 $0.021 ↑ Compare
2026-06-04 13:30 New test added 4.6 10.0 $0.003 ↓ Compare
2026-05-22 00:02 Suite changed 4.6 10.0 $0.005 Compare
2026-05-08 13:28 Suite changed 4.7 10.0 $0.005 Compare
2026-05-08 13:28 Suite changed 4.7 10.0 $0.005 Compare
2026-04-20 17:48 First recorded run 4.8 N/A $0.005 Compare

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

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 01:27 · Current run69/69 attempts4.99.79.84/23170,427307,670$0.04137.19s
2026-07-16 22:25 · New test added66/66 attempts5.19.710.04/22137,484144,407$0.02119.17s
Difference—-0.20.0-0.200+32943+163263+$0.021+18016ms

Benchmark coverage differs: 69/69 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.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Qwen3.5-9BnonevsMiMo-V2.5noneQwen3.5-9BnonevsHy4 previewnoneQwen3.5-9BnonevsLing 2.6 1tdefaultQwen3.5-9BnonevsGLM 4.7 FlashnoneQwen3.5-9BnonevsLaguna S 2.1highFree AvailableQwen3.5-9BnonevsMercury 2.5 PreviewdefaultQwen3.5-9BnonevsQwen3 Coder NextdefaultQwen3.5-9BnonevsNemotron 3.5 LightningmediumFree AvailableQwen3.5-9BnonevsInkling SmallnoneFree AvailableQwen3.5-9BnonevsNorth Mini CodedefaultFree Available

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.9 9.6
Anti-AI Tricks 3.1 9.9
Coding 3.9 7.8
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.0 10.0
General Intelligence 4.4 9.9
Instructions following 6.5 10.0
Puzzle Solving 3.2 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models