#132 Qwen3 Coder Next
none
Invalid SVG
- Cost
- $0.058
- Time
- 246.3s
- Tokens
- 64,126 tok
Qwen
Release: 2026-02-03
Tested on: 2026-05-21 23:44
qwen/qwen3-coder-next::none
80B total (3B active)MoEOpen source
(medium)
(none)
Summary
Qwen3 Coder Next scores 5.1 on AI BENCHY and ranks #132. It has 10.0 reliability, a 28.3% pass rate, $0.008 total cost, and 8.83s average response time.
What makes Qwen3 Coder Next unique: It stands out most in General Intelligence, where it ranks #1, while Puzzle Solving is its weakest area at #17. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- 80B total (3B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
5.1
Consistency
9.7
10.0
$0.008
Total Output Tokens
3,656
Total Input Tokens
0
Input Price
$0.110 / 1M
Output Price
$0.800 / 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 01:38 Re-test | 5.1 | 10.0 | $0.026 ↑ | Compare | |
| 2026-07-16 21:14 New test added | 5.1 | 10.0 | $0.025 ↓ | Compare | |
| 2026-06-04 13:09 New test added | 4.9 | 10.0 | $0.009 ↓ | Compare | |
| 2026-05-21 23:44 Suite changed | 5.1 | 10.0 | $0.008 | Current run | |
| 2026-04-14 00:56 First recorded run | 5.1 | N/A | $0.008 | 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 23:44 · Suite changed | 60/60 attempts | 5.1 | 9.7 | 10.0 | 5/20 | 1 | 3,656 | 0 | $0.008 | 8.83s |
| 2026-07-16 21:14 · New test added | 66/66 attempts | 5.1 | 9.7 | 10.0 | 5/22 | 1 | 11,808 | 134,218 | $0.025 | 9.12s |
| Difference | — | 0.0 | 0.0 | 0.0 | 0 | 0 | -8152 | -134218 | -$0.017 | -291ms |
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 Coder NextnonevsMistral Small 4mediumQwen3 Coder NextnonevsMiMo-V2.5noneQwen3 Coder NextnonevsMistral Small 4noneQwen3 Coder NextnonevsQwen3.5-9BnoneQwen3 Coder NextnonevsNemotron 3.5 LightningmediumFree AvailableQwen3 Coder NextnonevsNorth Mini CodenoneFree AvailableQwen3 Coder NextnonevsInklingnoneQwen3 Coder NextnonevsMiniMax M2.7mediumQwen3 Coder NextnonevsDots 3 Note PreviewnoneFree AvailableQwen3 Coder NextnonevsLaguna S 2.1lowFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.6 | 10.0 | |
| Coding | 5.4 | 6.9 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 3.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |