AI BENCHY
Your ad here

#78

Qwen3.6 27B

Qwen Release: 2026-04-20 Tested on: 2026-04-27 21:31 qwen/qwen3.6-27b::none
(medium) (none)

Score

5.9

Consistency

6.9

Total Cost

$0.027

Total Output Tokens

2,924

Input Price

$0.500 / 1M

Output Price

$2.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 54.6%

Flaky tests

4

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

Response Time (avg)

4.19s

Response Time (max): 10.18s

Response Time (total): 46.05s

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-04-27 21:46 New test added 6.0 10.0 $0.031 Compare
2026-04-27 21:31 First recorded run 5.9 10.0 $0.027 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal CostResponse Time (avg)
2026-04-27 21:31 · First recorded run5.96.910.04/1142,924$0.0274.19s
2026-04-27 21:46 · New test added6.07.210.07/1863,775$0.0314.00s
Difference-0.1-0.30.0-3-2-851-$0.004+186ms

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

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 4.0 1.6
Coding 10.0 10.0
Combined 3.0 10.0
Data parsing and extraction 9.9 10.0
Domain specific 6.5 10.0
General Intelligence 5.2 9.9
Instructions following 2.8 1.6
Tool Calling 9.5 10.0

Compared models