#97 Qwen3.5-Flash
none- Cost
- $0.003
- Time
- 47.4s
- Tokens
- 7,799 tok
Qwen
Release: 2026-02-24
Tested on: 2026-05-21 23:55
qwen/qwen3.5-flash-02-23::none
~35B total (~3B active)MoEClosedEstimated
(medium)
(none)
Summary
Qwen3.5-Flash scores 5.9 on AI BENCHY and ranks #97. It has 10.0 reliability, a 41.7% pass rate, $0.006 total cost, and 2.99s average response time.
What makes Qwen3.5-Flash unique: It stands out most in Domain specific, where it ranks #1, while Anti-AI Tricks is its weakest area at #18. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- Parameters
- ~35B total (~3B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Estimate from the nearest released Qwen3.5 Flash-class checkpoint.
5.9
Consistency
9.7
10.0
$0.006
Total Output Tokens
4,299
Total Input Tokens
0
Input Price
$0.065 / 1M
Output Price
$0.260 / 1M
Flaky tests
1
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 01:50 Re-test | 6.0 | 10.0 | $0.073 ↓ | Compare | |
| 2026-07-16 22:07 New test added | 6.1 | 10.0 | $0.073 ↓ | Compare | |
| 2026-06-04 13:25 New test added | 5.8 | 10.0 | $0.005 ↓ | Compare | |
| 2026-05-21 23:55 Suite changed | 5.9 | 10.0 | $0.006 | Current run | |
| 2026-04-11 01:19 First recorded run | 6.2 | N/A | $0.006 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-21 23:55 · Suite changed | 60/60 attempts | 5.9 | 9.7 | 10.0 | 8/20 | 1 | 4,299 | 0 | $0.006 | 2.99s |
| 2026-07-16 22:07 · New test added | 66/66 attempts | 6.1 | 9.3 | 10.0 | 8/22 | 2 | 209,201 | 282,347 | $0.073 | 25.28s |
| Difference | — | -0.2 | +0.4 | 0.0 | 0 | -1 | -204902 | -282347 | -$0.067 | -22297ms |
Benchmark coverage differs: 60/60 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-FlashnonevsGPT-5 NanomediumQwen3.5-FlashnonevsQwen3.5-35B-A3BnoneQwen3.5-FlashnonevsGPT-5.6 TerranoneQwen3.5-FlashnonevsStep 3.5 FlashmediumQwen3.5-FlashnonevsGemini 2.5 FlashnoneQwen3.5-FlashnonevsDots 3 Note PreviewmediumFree AvailableQwen3.5-FlashnonevsTrinity Large ThinkinglowQwen3.5-FlashnonevsGLM 5.3 FlashlowQwen3.5-FlashnonevsNemotron 3 UltranoneFree AvailableQwen3.5-FlashnonevsGPT-5.4 Mininone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.5 | 8.3 | |
| Coding | 6.8 | 10.0 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 7.7 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 3.1 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |