- Score
- 8.6 (+1.34 points)
- Total Cost (Current Price)
- $0.061 · 47.6% cheaper
- Response Time (avg)
- 7.51s · 24.7% faster
Qwen
Release: 2026-02-24
Tested on: 2026-10-01 01:05
qwen/qwen3.5-27b::none
27BDenseOpen source
(medium)
(none)
Summary
Qwen3.5-27B scores 7.2 on AI BENCHY and ranks #149. It has 10.0 reliability, a 47.8% pass rate, $0.116 total cost, and 9.98s average response time.
What makes Qwen3.5-27B unique: It stands out most in Agentic, where it ranks #1, while Anti-AI Tricks is its weakest area at #17.
Recommended alternatives
We recommend choosing this model instead:
Model facts
Researched on 2026-08-12
- Parameters
- 27B
- Architecture
- Dense
- Availability
- Open source
- License
- Apache-2.0
7.2
Consistency
9.4
10.0
$0.116
Total Output Tokens
36,422
Total Input Tokens
283,977
Input Price
$0.195 / 1M
Output Price
$1.560 / 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.
Flaky tests
2
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.
#149 Qwen3.5-27B
none- Cost
- $0.007
- Time
- 42.9s
- Tokens
- 4,273 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 01:05 Re-test | 7.2 | 10.0 | $0.116 | Current run | |
| 2026-07-16 22:01 New test added | 6.5 | 10.0 | $0.058 ↓ | Compare | |
| 2026-06-04 13:28 New test added | 5.7 | 10.0 | $0.015 ↓ | Compare | |
| 2026-05-21 23:59 Suite changed | 5.8 | 10.0 | $0.017 | Compare | |
| 2026-04-11 01:19 First recorded run | 5.9 | N/A | $0.016 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-10-01 01:05 · Current run | 69/69 attempts | 7.2 | 9.4 | 10.0 | 10/23 | 2 | 36,422 | 283,977 | $0.116 | 9.98s |
| 2026-07-16 22:01 · New test added | 66/66 attempts | 6.5 | 9.3 | 10.0 | 8/22 | 2 | 24,321 | 102,316 | $0.058 | 4.76s |
| Difference | — | +0.7 | +0.1 | 0.0 | +2 | 0 | +12101 | +181661 | +$0.058 | +5220ms |
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.
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
Qwen3.5-27BnonevsGemini 3.5 Flash LitemediumQwen3.5-27BnonevsQwen3.5 Plus 2026-02-15mediumQwen3.5-27BnonevsQwen3.6 PlusmediumQwen3.5-27BnonevsQwen3.8 27BmediumFree AvailableQwen3.5-27BnonevsLongCat 2.0highQwen3.5-27BnonevsGemini 3.8 FlashlowQwen3.5-27BnonevsGemini 2.5 FlashmediumQwen3.5-27BnonevsClaude Opus 4.8lowQwen3.5-27BnonevsGrok 4.7mediumQwen3.5-27BnonevsQwen3.7 Flashhigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 4.8 | 10.0 | |
| Coding | 5.8 | 10.0 | |
| Combined | 6.4 | 5.8 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.0 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 6.7 | 7.9 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |