- Score
- 8.3 (+3.61 points)
- Total Cost (Current Price)
- $0.047 · 33.0% cheaper
- Response Time (avg)
- 18.07s · 6.4% slower
Qwen
Release: 2026-02-03
Tested on: 2026-10-01 00:26
qwen/qwen3-coder-next::medium
80B total (3B active)MoEOpen source
(medium)
(none)
Summary
Qwen3 Coder Next scores 4.7 on AI BENCHY and ranks #323. It has 10.0 reliability, a 24.6% pass rate, $0.071 total cost, and 16.97s 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 #10.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 5.2 (+0.53 points)
- Total Cost (Current Price)
- $0.004 · 95.1% cheaper
- Response Time (avg)
- 3.40s · 80.0% faster
- Score
- 5.0 (+0.31 points)
- Total Cost (Current Price)
- $0.000 · 100.0% cheaper
- Response Time (avg)
- 5.36s · 68.4% faster
Model facts
Researched on 2026-08-12
- Parameters
- 80B total (3B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
4.7
Consistency
8.7
10.0
Total Output Tokens
40,395
Total Input Tokens
311,647
Input Price
$0.120 / 1M
Output Price
$0.800 / 1M
Cache Read Price
$0.070 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
4
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.
#323 Qwen3 Coder Next
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 00:26 Re-test | 4.7 | 10.0 | $0.071 ↑ | Current run | |
| 2026-07-16 21:16 New test added | 4.7 | 10.0 | $0.032 ↓ | Compare | |
| 2026-06-04 13:09 New test added | 4.6 | 10.0 | $0.008 ↓ | Compare | |
| 2026-05-21 23:45 Suite changed | 4.7 | 10.0 | $0.008 | Compare | |
| 2026-04-14 00:56 First recorded run | 4.7 | N/A | $0.008 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-06-04 15:40 | $0.110 / 1M | $0.800 / 1M | N/A | N/A |
| 2026-08-14 12:51 | $0.120 / 1M | $0.800 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $0.120 / 1M | $0.800 / 1M | $0.070 / 1M | N/A |
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 NextmediumvsGranite 4.2 8BhighQwen3 Coder NextmediumvsDeepSeek V3.2noneQwen3 Coder NextmediumvsLaguna S 2.1noneFree AvailableQwen3 Coder NextmediumvsGPT-5.4 NanononeQwen3 Coder NextmediumvsNorth Mini CodenoneFree AvailableQwen3 Coder NextmediumvsLaguna S 2.1lowFree AvailableQwen3 Coder NextmediumvsNemotron 3.5 LightningmediumFree AvailableQwen3 Coder NextmediumvsNemotron 3.5 LightninglowFree AvailableQwen3 Coder NextmediumvsMercury 2.5 PreviewnoneQwen3 Coder NextmediumvsLing 2.6 Flashnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 5.0 | 10.0 | |
| Anti-AI Tricks | 3.5 | 8.1 | |
| Coding | 3.7 | 7.2 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 6.3 | 3.4 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 3.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |