- Score
- 8.6 (+2.07 points)
- Total Cost (Current Price)
- $0.061 · 92.7% cheaper
- Response Time (avg)
- 7.51s · 87.5% faster
Qwen
Release: 2026-04-20
Tested on: 2026-10-01 00:45
qwen/qwen3.6-35b-a3b::medium
35B total (3B active)MoEOpen source
(medium)
(none)
Summary
Qwen3.6 35B A3B scores 6.5 on AI BENCHY and ranks #238. It has 10.0 reliability, a 58.0% pass rate, $0.834 total cost, and 59.92s average response time.
What makes Qwen3.6 35B A3B unique: It stands out most in Instructions following, where it ranks #1, while Combined is its weakest area at #14. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 9.4 (+2.86 points)
- Total Cost (Current Price)
- $0.183 · 78.1% cheaper
- Response Time (avg)
- 6.24s · 89.6% faster
- Score
- 8.3 (+1.76 points)
- Total Cost (Current Price)
- $0.047 · 94.4% cheaper
- Response Time (avg)
- 18.07s · 69.8% faster
Model facts
Researched on 2026-08-12
- Parameters
- 35B total (3B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
6.5
Consistency
9.0
10.0
Total Output Tokens
769,570
Total Input Tokens
282,192
Input Price
$0.150 / 1M
Output Price
$1.000 / 1M
Cache Read Price
$0.050 / 1M
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
3
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.
#238 Qwen3.6 35B A3B
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 00:45 Re-test | 6.5 | 10.0 | $0.834 ↑ | Current run | |
| 2026-07-16 22:06 New test added | 6.7 | 10.0 | $0.746 ↑ | Compare | |
| 2026-06-04 13:20 New test added | 7.4 | 10.0 | $0.146 ↑ | Compare | |
| 2026-05-22 00:02 Suite changed | 7.8 | 9.4 | $0.126 | Compare | |
| 2026-04-27 23:06 Initial run | 8.8 | 10.0 | $0.104 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-06-04 15:40 | $0.140 / 1M | $1.000 / 1M | N/A | N/A |
| 2026-08-14 12:51 | $0.150 / 1M | $1.000 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $0.150 / 1M | $1.000 / 1M | $0.050 / 1M | N/A |
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 35B A3BmediumvsMinimax M3.1 FlashhighFree AvailableQwen3.6 35B A3BmediumvsMercury 2.5 PreviewhighQwen3.6 35B A3BmediumvsClaude Sonnet 5.5mediumQwen3.6 35B A3BmediumvsMercury 2.5highQwen3.6 35B A3BmediumvsKAT-Coder-Pro V2.5lowQwen3.6 35B A3BmediumvsBeam 1.0 501B A23BxhighQwen3.6 35B A3BmediumvsBeam 1.0 501B A23BmediumQwen3.6 35B A3BmediumvsGLM 5.3lowQwen3.6 35B A3BmediumvsStep 3.7 FlashhighQwen3.6 35B A3BmediumvsGLM 5.1none
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 6.1 | 3.1 | |
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 7.7 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 4.4 | |
| General Intelligence | 4.4 | 9.9 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 8.0 | 10.0 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |