#14 Qwen3.6 Max Preview
medium- Cost
- $0.024
- Time
- 76.5s
- Tokens
- 3,861 tok
Qwen
Release: 2026-04-20
Tested on: 2026-05-21 23:59
qwen/qwen3.6-max-preview::medium
~1T total (~40B active)MoEClosedEstimated
(medium)
(none)
Summary
Qwen3.6 Max Preview scores 8.4 on AI BENCHY and ranks #14. It has 10.0 reliability, a 80.0% pass rate, $1.036 total cost, and 58.41s average response time.
Model facts
Researched on 2026-08-12
- Parameters
- ~1T total (~40B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the count.
8.4
Consistency
9.2
10.0
$1.036
Total Output Tokens
133,033
Total Input Tokens
0
Input Price
$1.040 / 1M
Output Price
$6.240 / 1M
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.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 01:45 Re-test | 8.6 | 10.0 | $1.132 ↓ | Compare | |
| 2026-07-16 21:55 New test added | 8.4 | 9.9 | $1.143 ↓ | Compare | |
| 2026-06-04 13:25 New test added | 8.5 | 10.0 | $0.960 ↓ | Compare | |
| 2026-05-21 23:59 Suite changed | 8.4 | 10.0 | $1.036 | Current run | |
| 2026-04-27 23:07 Initial run | 8.8 | 10.0 | $0.823 | 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 23:59 · Suite changed | 60/60 attempts | 8.4 | 9.2 | 10.0 | 15/20 | 2 | 133,033 | 0 | $1.036 | 58.41s |
| 2026-08-14 01:45 · Re-test | 66/66 attempts | 8.6 | 9.3 | 10.0 | 17/22 | 2 | 170,373 | 79,249 | $1.132 | 66.52s |
| Difference | — | -0.2 | -0.1 | 0.0 | -2 | 0 | -37340 | -79249 | -$0.096 | -8109ms |
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
Qwen3.6 Max PreviewmediumvsClaude Fable 5mediumQwen3.6 Max PreviewmediumvsQwen3.8 MaxlowQwen3.6 Max PreviewmediumvsMuse Spark 1.1mediumQwen3.6 Max PreviewmediumvsGPT-5.4mediumQwen3.6 Max PreviewmediumvsMuse Spark 1.2mediumQwen3.6 Max PreviewmediumvsDeepSeek V4.1 FlashlowQwen3.6 Max PreviewmediumvsMuse Spark 1.2highQwen3.6 Max PreviewmediumvsDeepSeek V4.1 FlashhighQwen3.6 Max PreviewmediumvsClaude Opus 4.7mediumQwen3.6 Max PreviewmediumvsDeepSeek V4.1 Flashmedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 8.2 | 6.7 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |