AI BENCHY
Compare
❤️ Made by XCS

Model Name

Qwen: Qwen3.5 Plus 2026-02-15

Last updated at : Feb 19, 2026

Metric Qwen: Qwen3.5 Plus 2026-02-15
Rank#4
CompanyQwen
Score 8.42
Consistency 9.30
Cost per result 2.3151
Total Cost $0.23151
Tests Correct 10/12
Attempt pass rate 86.1%
Flaky tests 1
Output Tokens 802
Reasoning Tokens 93,972

Category Breakdown

Category Fully passed tests Score Consistency Attempt pass rate Flaky tests Reasoning score Cost
Anti-AI Tricks 2/2 10.00 10.00 100.0% 0 9.17 $0.00855
Data parsing and extraction 2/2 10.00 10.00 100.0% 0 9.61 $0.03952
Domain specific 1/3 4.00 7.21 44.4% 1 7.28 $0.10564
Instructions following 2/2 9.50 9.99 100.0% 0 9.33 $0.02275
Puzzle Solving 3/3 10.00 10.00 100.0% 0 8.28 $0.05508

Compared models

Compare Qwen: Qwen3.5 Plus 2026-02-15 against...

#3 · Google

Google: Gemini 3 Pro Preview

Reasoning (medium)

Score: 8.42

Consistency: 10.00

Attempt pass rate: 83.3%

Flaky tests: 0

Cost per result: 0.8028

Tests Correct: 10/12

Total Cost: $0.08029

Compare

#5 · OpenAI

OpenAI: GPT-5.2

Reasoning (medium)

Score: 7.92

Consistency: 9.30

Attempt pass rate: 80.6%

Flaky tests: 1

Cost per result: 2.2838

Tests Correct: 9/12

Total Cost: $0.20554

Compare

#2 · Google

Google: Gemini 3.1 Pro Preview

Reasoning (medium)

Score: 9.25

Consistency: 10.00

Attempt pass rate: 91.7%

Flaky tests: 0

Cost per result: 2.5543

Tests Correct: 11/12

Total Cost: $0.28097

Compare

Quick Compare

Compare Qwen: Qwen3.5 Plus 2026-02-15 against...