Qwen 3.5 397B by Qwen demonstrates strong general intelligence, excellent coding ability. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Human preference ELO from blind head-to-head votes
LMSYS / HuggingFaceMassive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardArtificial Analysis composite intelligence score across 10 sub-benchmarks
Artificial Analysis (via OpenRouter)Coding Benchmarks
Artificial Analysis composite coding score
Artificial Analysis (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Artificial Analysis composite score for multi-step tool-using tasks
Artificial Analysis (via OpenRouter)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 1 provider
The same model costs different amounts depending on who serves it.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Venice AI | $0.75 | $4.5 | — | 128K | — |
Qwen 3.5 397B — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Qwen 3.5 397B With
Qwen 3.5 397B — Frequently Asked Questions
How intelligent is Qwen 3.5 397B?
Qwen 3.5 397B scores 1350 on the Chatbot Arena ELO rating, making it a high-performing AI model. This score is based on blind head-to-head human preference voting.
How much does Qwen 3.5 397B cost?
Qwen 3.5 397B costs $0.55 per 1M input tokens and $3.5 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is Qwen 3.5 397B?
Qwen 3.5 397B generates output at 45 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 600 ms.
How good is Qwen 3.5 397B at coding?
Qwen 3.5 397B achieves 76.4% on SWE-bench Verified, demonstrating excellent real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is Qwen 3.5 397B at math and reasoning?
Qwen 3.5 397B scores 87.0% on the MATH benchmark (competition-level mathematics). It also achieves 62.0% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of Qwen 3.5 397B?
Qwen 3.5 397B has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Qwen 3.5 397B?
Qwen 3.5 397B was created by Qwen. It is classified as a open source model in our catalogue.
Is Qwen 3.5 397B open source?
Yes, Qwen 3.5 397B is an open-source model. The model weights are publicly available for download and self-hosting.