Alibaba
Qwen3.5-397B-A17B
A large, open-source model from Alibaba Cloud with competitive performance on leaderboards.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Overall rank
- #72
- Tier
- B
- Score
- 68.5
- Main category
- Overall
Strengths
- Available as an open-source model, allowing for greater flexibility.
- Offers a very low price point for its performance class.
- Part of a family of ultra-efficient small models.
Considerations
- As an open-weight model, it requires users to manage their own infrastructure for deployment.
- The complex model name may be less memorable or marketable than competitors.
Price
$0.60 / 1M input, $3.60 / 1M output tokens
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 70.0
- 55% of score
- Reputation
- 72.0
- 35% of score
- Recency
- 48.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
- Pricing
- Benchmark
- Reputation
- Feature list
Checked against the sources listed below.
Sources
- Artificial Analysis: Qwen3.5-397B-A17B (opens in a new tab)Accessed:
- Qwen blog: Qwen3.5 (opens in a new tab)Accessed:
- The Decoder: Qwen 3.8 open-weights release (opens in a new tab)Accessed:
- Codersera: Qwen 3.5 to 3.8 guide (opens in a new tab)Accessed:
- DemandSphere (opens in a new tab)Accessed:
Show 8 more sources
- Technical Performance | 2026 AI Index Report | Stanford HAI (opens in a new tab)Accessed:
- Introducing the AI Frontier Model Tracker | DemandSphere (opens in a new tab)Accessed:
- 15 Best AI Models in 2026 for Every Use Case: APIs vs Open Weights (opens in a new tab)Accessed:
- Northflank — Top AI Companies 2026 (opens in a new tab)Accessed:
- The 10 Best AI Models in 2026 - Towards AI (opens in a new tab)Accessed:
- Pluralsight: The best AI models in 2026 (opens in a new tab)Accessed:
- AI Leaderboard 2026 - LLM Stats (opens in a new tab)Accessed:
- LinkedIn - Best AI Models April 2026 (opens in a new tab)Accessed:
Similar models
- Llama 4Meta#59 · Tier A · Score 74.8Compare
- Gemma 4 31BGoogle#64 · Tier A · Score 73.0Compare
- Ministral 3 14BMistral AI#74 · Tier B · Score 68.3Compare
- Llama 4 MaverickMeta#76 · Tier B · Score 65.7Compare