#27 Qwen3.7 Max
none- Cost
- $0.046
- Time
- 195.0s
- Tokens
- 12,171 tok
Qwen
Release: 2026-05-22
Tested on: 2026-05-21 23:54
qwen/qwen3.7-max::none
~1T total (~40B active)MoEClosedEstimated
(medium)
(none)
Summary
Qwen3.7 Max scores 7.9 on AI BENCHY and ranks #27. It has 10.0 reliability, a 70.0% pass rate, $0.101 total cost, and 1.30s average response time.
What makes Qwen3.7 Max 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
- ~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.
7.9
Consistency
10.0
10.0
$0.101
Total Output Tokens
1,988
Total Input Tokens
0
Input Price
$2.500 / 1M
Output Price
$7.500 / 1M
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.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 01:44 Re-test | 7.4 | 9.9 | $0.197 ↓ | Compare | |
| 2026-07-16 21:33 New test added | 7.4 | 9.9 | $0.197 ↓ | Compare | |
| 2026-06-04 13:21 New test added | 7.7 | 10.0 | $0.054 ↓ | Compare | |
| 2026-05-21 23:54 Initial run | 7.9 | 10.0 | $0.101 | Current run |
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 23:54 · Initial run | 60/60 attempts | 7.9 | 10.0 | 10.0 | 14/20 | 0 | 1,988 | 0 | $0.101 | 1.30s |
| 2026-08-14 01:44 · Re-test | 66/66 attempts | 7.4 | 10.0 | 9.9 | 15/22 | 0 | 12,446 | 95,992 | $0.197 | 4.56s |
| Difference | — | +0.5 | 0.0 | +0.1 | -1 | 0 | -10458 | -95992 | -$0.097 | -3261ms |
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
Qwen3.7 MaxnonevsGemini 3.1 Flash Lite PreviewmediumQwen3.7 MaxnonevsKimi K2.7 CodemediumQwen3.7 MaxnonevsGrok Build 0.1mediumQwen3.7 MaxnonevsGPT-5.6 LunamediumQwen3.7 MaxnonevsGPT-5.4 MinimediumQwen3.7 MaxnonevsLongCat 2.0mediumQwen3.7 MaxnonevsQwen3.5-27BmediumQwen3.7 MaxnonevsQwen3.8 2.4T A95BhighQwen3.7 MaxnonevsQwen3.5 Plus 2026-02-15mediumQwen3.7 MaxnonevsGrok 4.6low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.5 | 10.0 | |
| 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 | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |