Model benchmark
Qwen3 Coder 480B A35B (free):
AI recommendation benchmark.
How strongly does Qwen3 Coder 480B A35B (free) recommend a business when answering buyer questions—and how much does naming the business change its answer?
A sample still growing.
Recommendation scores will appear once enough distinct businesses have eligible analyses. Missing benchmarks are not zero scores.
Explore the provider
Qwen models, side by side.
Compare recommendation behavior and brand recognition. Open a model for its findings and sample details.
| Model | Organic / 100 | Mentioned / 100 | Gap | Unprompted inclusion | Recognized |
|---|---|---|---|---|---|
qwen/qwen3.8-max-prime Insufficient data |
— | — | — | — | |
qwen/qwen3.8-omni-flash Insufficient data |
— | — | — | — | |
qwen/qwen3.8-max-0902 Insufficient data |
— | — | — | — | |
qwen/qwen3.8-flash Insufficient data |
— | — | — | — | |
qwen/qwen3.8-27b Insufficient data |
— | — | — | — | |
qwen/qwen3.8-2.4t-a95b Insufficient data |
— | — | — | — | |
qwen/qwen3.7-flash Insufficient data |
— | — | — | — | |
qwen/qwen3.7-plus Insufficient data |
— | — | — | — | |
qwen/qwen3.7-max Insufficient data |
— | — | — | — | |
qwen/qwen3.5-plus-20260420 Insufficient data |
— | — | — | — | |
qwen/qwen3.6-flash Insufficient data |
— | — | — | — | |
qwen/qwen3.6-35b-a3b Insufficient data |
— | — | — | — | |
qwen/qwen3.6-max-preview Insufficient data |
— | — | — | — | |
qwen/qwen3.6-27b Insufficient data |
— | — | — | — | |
qwen/qwen3.6-plus Insufficient data |
— | — | — | — | |
qwen/qwen3.5-9b Insufficient data |
— | — | — | — | |
qwen/qwen3.5-35b-a3b Insufficient data |
— | — | — | — | |
qwen/qwen3.5-27b Insufficient data |
— | — | — | — | |
qwen/qwen3.5-122b-a10b Insufficient data |
— | — | — | — | |
qwen/qwen3.5-flash-02-23 Insufficient data |
— | — | — | — | |
qwen/qwen3.5-plus-02-15 Insufficient data |
— | — | — | — | |
qwen/qwen3.5-397b-a17b Insufficient data |
— | — | — | — | |
qwen/qwen3-max-thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-coder-next Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-32b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-8b-thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-8b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-30b-a3b-thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-30b-a3b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-235b-a22b-thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-vl-235b-a22b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-max Insufficient data |
— | — | — | — | |
qwen/qwen3-coder-plus Insufficient data |
— | — | — | — | |
qwen/qwen3-coder-flash Insufficient data |
— | — | — | — | |
qwen/qwen3-next-80b-a3b-thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-next-80b-a3b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-next-80b-a3b-instruct:free Insufficient data |
— | — | — | — | |
qwen/qwen-plus-2025-07-28 Insufficient data |
— | — | — | — | |
qwen/qwen-plus-2025-07-28:thinking Insufficient data |
— | — | — | — | |
qwen/qwen3-30b-a3b-thinking-2507 Insufficient data |
— | — | — | — | |
qwen/qwen3-coder-30b-a3b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen3-30b-a3b-instruct-2507 Insufficient data |
— | — | — | — | |
qwen/qwen3-235b-a22b-thinking-2507 Insufficient data |
— | — | — | — | |
qwen/qwen3-coder Insufficient data |
— | — | — | — | |
qwen/qwen3-coder:free Insufficient data |
— | — | — | — | |
qwen/qwen3-235b-a22b-2507 Insufficient data |
— | — | — | — | |
qwen/qwen3-30b-a3b Insufficient data |
— | — | — | — | |
qwen/qwen3-8b Insufficient data |
— | — | — | — | |
qwen/qwen3-14b Insufficient data |
— | — | — | — | |
qwen/qwen3-32b Insufficient data |
— | — | — | — | |
qwen/qwen3-235b-a22b Insufficient data |
— | — | — | — | |
qwen/qwen2.5-vl-72b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen-plus Insufficient data |
— | — | — | — | |
qwen/qwen-2.5-coder-32b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen-2.5-7b-instruct Insufficient data |
— | — | — | — | |
qwen/qwen-2.5-72b-instruct Insufficient data |
— | — | — | — | |
| No models match this search. | |||||
Compare with context. Samples differ between models. Low gap does not mean high visibility: read both scores together. Recognition is measured separately through Domain Clarity.
About this model
Qwen3 Coder 480B A35B (free) in AEOchamp.
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Provider
Qwen
Context window
1,048,576 tokens
Model status
Inactive
Analysis type
Structured analysis unavailable
Model details come from AEOchamp’s model catalog. These API benchmark results do not represent every consumer chat product or browsing configuration.
How to read the data
A benchmark with its workings shown.
The numbers describe AEOchamp’s tests. They are not search rankings or a universal model quality score.
What do Organic and Mentioned mean?
Organic asks a buyer question without supplying the target domain and checks whether the business appears in the returned recommendation list. Mentioned asks the same question with the target domain supplied. Both use the model’s existing knowledge, without browsing.
How is the recommendation gap calculated?
For each completed question pair, subtract the Organic score from the Mentioned score. Average the pairs within each domain, then average across distinct domains. A +39 gap means 39 score points, not a 39% improvement.
What happens if a business is absent?
A completed Organic result contributes 0 if the target business is absent from the returned list. Unfinished or failed pairs are excluded from both averages. Absence from this list does not establish that the model has never heard of the business.
Can I compare different models fairly?
These tables show each model’s available sample, which may include different businesses and questions. They are descriptive comparisons, not a controlled leaderboard. A fair head-to-head test needs the same domains, questions and test settings.
Which questions and businesses are included?
The benchmark uses completed baseline question pairs and counts each distinct domain once per model. Custom questions and internal/demo projects are excluded. Local fake analyses and results without completed training run records are excluded. When multiple projects track the same domain, only its most recently updated eligible project is included for that model.
How much data is enough to publish?
Scores are published only when enough distinct businesses have eligible analyses. Only aggregate scores are public; sample counts, customer domains, buyer questions and raw answers are not shown.
Latest eligible results are used without a time cutoff. Aggregates refresh every 15 minutes. Recognition samples are separate from User Intent samples. Inclusion is averaged within each domain before averaging across domains. Rounded averages may not subtract to the displayed paired gap.
From the average to your business
The benchmark shows the pattern.
AEOchamp shows where you stand.
Find out whether AI models recognize your business, how they describe it, and whether they recommend it for the questions your buyers ask.
- Check your category, audience and jobs
- Compare Organic and Mentioned scores
- Find positioning gaps worth investigating
Domain Clarity + User Intent, in one place.