#61 Qwen3.8 27B
low- Cost
- N/A
- Time
- 92.8s
- Tokens
- 6,902 tok
Qwen
Release: 2026-08-14
Tested on: 2026-08-14 23:33
qwen/qwen3.8-27b::low
27.3BOtherWeights available
Summary
Qwen3.8 27B scores 7.9 on AI BENCHY and ranks #61. It has 10.0 reliability, a 68.2% pass rate, N/A total cost, and 39.11s average response time.
Model facts
Researched on 2026-08-14
- Parameters
- 27.3B
- Architecture
- Other
- Availability
- Weights available
- License
- Apache-2.0
Exact local Q4_K_M GGUF reports 27.3B parameters and a hybrid attention/SSM architecture through Ollama model details. Tested locally on an NVIDIA GeForce RTX 3090.
7.9
Consistency
10.0
10.0
Total Output Tokens
169,329
Total Input Tokens
99,705
Input Price
N/A
Output Price
N/A
Flaky tests
0
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.
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
Qwen3.8 27BlowvsStep 3.7 FlashmediumQwen3.8 27BlowvsQwen3.7 PlusmediumQwen3.8 27BlowvsGPT-5.2 ChatnoneQwen3.8 27BlowvsQwen3.6 PlusmediumQwen3.8 27BlowvsKimi K3maxQwen3.8 27BlowvsGemini 3.5 Flash LitemediumQwen3.8 27BlowvsGPT-5.6 TerrahighQwen3.8 27BlowvsGLM 5.2mediumQwen3.8 27BlowvsInklingmediumQwen3.8 27BlowvsGPT-5.6 Terramedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 7.7 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 5.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 7.7 | 10.0 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |