LLM Reference

Qwen3.5-35B-A3B

Released
2026-02-24
Last refreshed
2026-06-29
Status
Researched 89d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

Qwen3.5-35B-A3B is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 262k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Qwen3.5
Released
2026-02-24
Context
262k
Parameters
35B
Architecture
Mixture of Experts
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$1.00
Input / 1M
$0.139

Cheapest of 2 routes · OpenRouter

About

Alibaba's Qwen3.5-35B-A3B is a Mixture-of-Experts model released February 24, 2026, with 35B total parameters and 3B active during inference. Part of the Qwen3.5 series with a 262K native context window (extendable to ~1M tokens). Optimized for high inference throughput (78+ tokens/second on NVIDIA hardware). Open-source under Apache 2.0.

Qwen3.5-35B-A3B is an open-source model in the Qwen3.5 family. The structured metadata tracks a 262k-token context window, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter and Novita AI, with the cheapest tracked route listed at $0.139 input and $1 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 84.5, MMMU Pro 75.1, and SWE-rebench 53.7.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ B

3 relevant benchmarks in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
OpenRouter$0.139$1.00
Serverless
Novita AI$0.250$2.00
Serverless

Capabilities

ReasoningFunction CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(9)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A84.5diamondhttps://pricepertoken.com/leaderboards/benchmark/gpqa
MMMU Pro75.1LLM-Stats aggregatorhttps://llm-stats.com/benchmarks/mmmu-pro
SWE-rebench53.7pass@1 (best of 5 runs)https://swe-rebench.com/leaderboard
Berkeley Function Calling Leaderboard v367.3BFCL-V4, from official model card (accuracy)https://huggingface.co/Qwen/Qwen3.5-35B-A3B
Humanity's Last Exam22.4HLE with CoT, no tools, from official model card (accuracy)https://huggingface.co/Qwen/Qwen3.5-35B-A3B
LiveCodeBench74.6LiveCodeBench v6 (pass@1)https://huggingface.co/Qwen/Qwen3.5-35B-A3B
MMLU PRO85.3From official HuggingFace model card (accuracy)https://huggingface.co/Qwen/Qwen3.5-35B-A3B
SWE-bench Verified69.2From official model card (resolved)https://huggingface.co/Qwen/Qwen3.5-35B-A3B
τ-bench81.2TAU2-Bench, from official model card (accuracy)https://huggingface.co/Qwen/Qwen3.5-35B-A3B

Migration checks

No linked migration route is available for this model yet.

Compare Qwen3.5-35B-A3B with other models

Show all 20 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has a context window of 262k tokens.

How much does Qwen3.5-35B-A3B cost?

Qwen3.5-35B-A3B pricing ranges from $0.139/1M to $0.25/1M input tokens depending on the provider.

When was Qwen3.5-35B-A3B released?

Qwen3.5-35B-A3B was released on 2026-02-24.

Which providers offer Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B is available from 2 providers: OpenRouter, Novita AI.

What benchmarks has Qwen3.5-35B-A3B been tested on?

Qwen3.5-35B-A3B has been evaluated on 9 benchmarks, including Google-Proof Q&A, MMMU Pro, SWE-rebench, Berkeley Function Calling Leaderboard v3, Humanity's Last Exam.