#243 Qwen3.6 27B
none- Cost
- $0.009
- Time
- 83.0s
- Tokens
- 4,549 tok
Qwen
Release: 2026-04-20
Tested on: 2026-08-14 01:40
qwen/qwen3.6-27b::none
27BDenseOpen source
(medium)
(none)
Summary
Qwen3.6 27B scores 5.5 on AI BENCHY and ranks #243. It has 10.0 reliability, a 45.5% pass rate, $0.062 total cost, and 10.62s average response time.
What makes Qwen3.6 27B unique: It stands out most in Coding, where it ranks #2, while Instructions following is its weakest area at #10.
Model facts
Researched on 2026-08-12
- Parameters
- 27B
- Architecture
- Dense
- Availability
- Open source
- License
- Apache-2.0
5.5
Consistency
7.6
10.0
Total Output Tokens
16,156
Total Input Tokens
95,805
Input Price
$0.300 / 1M
Output Price
$2.000 / 1M
Flaky tests
6
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 01:40 Re-test | 5.5 | 10.0 | $0.062 ↓ | Current run | |
| 2026-07-16 21:24 New test added | 5.5 | 10.0 | $0.087 ↑ | Compare | |
| 2026-06-04 13:16 New test added | 5.6 | 10.0 | $0.028 ↓ | Compare | |
| 2026-05-21 23:48 Suite changed | 5.8 | 10.0 | $0.032 | 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 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 01:40 · Current run | 66/66 attempts | 5.5 | 7.6 | 10.0 | 7/22 | 6 | 16,156 | 95,805 | $0.062 | 10.62s |
| 2026-05-21 23:48 · Suite changed | 60/60 attempts | 5.8 | 7.5 | 10.0 | 7/20 | 6 | 3,812 | 0 | $0.032 | 3.87s |
| Difference | — | -0.2 | +0.1 | 0.0 | 0 | 0 | +12344 | +95805 | +$0.030 | +6754ms |
Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 60/60 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 15:40 | $0.290 / 1M | $3.200 / 1M |
| 2026-06-10 13:42 | $0.290 / 1M | $2.400 / 1M |
| 2026-06-12 18:42 | $0.288 / 1M | $3.100 / 1M |
| 2026-06-17 10:07 | $0.289 / 1M | $3.170 / 1M |
| 2026-06-29 01:00 | $0.260 / 1M | $2.386 / 1M |
| 2026-06-30 21:25 | $0.286 / 1M | $2.400 / 1M |
| 2026-07-16 15:36 | $0.450 / 1M | $2.700 / 1M |
| 2026-08-14 12:51 | $0.600 / 1M | $3.600 / 1M |
| 2026-09-04 19:19 | $0.300 / 1M | $2.000 / 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
Qwen3.6 27BnonevsHy4 previewlowQwen3.6 27BnonevsQwen3.8 27BnoneQwen3.6 27BnonevsNemotron 3.5 LightninghighFree AvailableQwen3.6 27BnonevsDeepSeek V4 Flash 0423noneQwen3.6 27BnonevsKAT-Coder-Air V2.5mediumQwen3.6 27BnonevsDeepSeek V4.1 FlashnoneQwen3.6 27BnonevsGemma 4 26B A4BnoneFree AvailableQwen3.6 27BnonevsLaguna S 2.1mediumFree AvailableQwen3.6 27BnonevsKAT-Coder-Air V2.5highQwen3.6 27BnonevsKAT-Coder-Air V2.5low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.8 | 3.7 | |
| Coding | 5.5 | 10.0 | |
| Combined | 3.2 | 9.1 | |
| Data parsing and extraction | 7.3 | 5.8 | |
| Domain specific | 7.7 | 10.0 | |
| General Intelligence | 5.2 | 9.9 | |
| Instructions following | 6.2 | 5.8 | |
| Puzzle Solving | 5.3 | 7.2 | |
| Tool Calling | 9.5 | 10.0 | |
| Trivia | 3.0 | 10.0 |