#65 Qwen3.5-35B-A3B
medium- Cost
- $0.009
- Time
- 71.4s
- Tokens
- 8,631 tok
Qwen
Release: 2026-02-24
Tested on: 2026-06-04 13:42
qwen/qwen3.5-35b-a3b::medium
35B total (3B active)MoEOpen source
(medium)
(none)
Summary
Qwen3.5-35B-A3B scores 7.1 on AI BENCHY and ranks #65. It has 8.9 reliability, a 73.0% pass rate, $0.401 total cost, and 72.57s average response time.
What makes Qwen3.5-35B-A3B unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Model facts
Researched on 2026-08-12
- Parameters
- 35B total (3B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
7.1
Consistency
7.2
8.9
Total Output Tokens
394,207
Total Input Tokens
42,196
Input Price
$0.140 / 1M
Output Price
$1.000 / 1M
Flaky tests
7
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 01:57 Re-test | 6.1 | 10.0 | $1.623 ↑ | Compare | |
| 2026-07-16 22:51 New test added | 6.2 | 10.0 | $0.837 ↓ | Compare | |
| 2026-06-04 13:42 New test added | 7.1 | 8.9 | $0.401 ↓ | Current run | |
| 2026-05-22 00:15 Suite changed | 7.0 | 6.7 | $0.547 | Compare | |
| 2026-04-11 01:44 First recorded run | 7.4 | N/A | $0.398 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-06-04 13:42 · New test added | 63/63 attempts | 7.1 | 7.2 | 8.9 | 11/21 | 7 | 394,207 | 42,196 | $0.401 | 72.57s |
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 7.4 | 6.7 | N/A | 10/18 | 7 | 218,898 | 0 | $0.398 | 44.51s |
| Difference | — | -0.3 | +0.5 | +1 | 0 | +175309 | +42196 | +$0.003 | +28062ms |
Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 54/54 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 14:42 | $0.140 / 1M | $1.000 / 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
Qwen3.5-35B-A3BmediumvsGemini 3.1 Flash LiteminimalQwen3.5-35B-A3Bmediumvsgpt-oss-120bmediumQwen3.5-35B-A3BmediumvsClaude Sonnet 5noneQwen3.5-35B-A3BmediumvsQwen3.7 FlashnoneQwen3.5-35B-A3BmediumvsGPT-5.6 LunalowQwen3.5-35B-A3BmediumvsGemini 3.1 Flash LitenoneQwen3.5-35B-A3BmediumvsGemma 4 31BmediumFree AvailableQwen3.5-35B-A3BmediumvsQwen3.5-FlashmediumQwen3.5-35B-A3BmediumvsSeed-2.0-LitenoneQwen3.5-35B-A3BmediumvsInklinglow
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 5.9 | 7.2 | |
| Combined | 4.7 | 1.6 | |
| Data parsing and extraction | 7.3 | 5.9 | |
| Domain specific | 4.1 | 4.4 | |
| General Intelligence | 2.8 | 1.6 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 8.2 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |