LLM Reference

Qwen3.6-35B-A3B

Released
2026-04-16
Last refreshed
2026-06-29
Status
Researched 46d ago
Open sourceCommercial use: permittedMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Qwen3.6-35B-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

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Qwen3.6
Released
2026-04-16
Context
262k
Parameters
35B
Architecture
Mixture of Experts
Specialization
code
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
$0.150

Cheapest of 2 routes · OpenRouter

About

Qwen3.6-35B-A3B is an open-weight multimodal MoE model with 35B total parameters and 3B activated per token, released April 2026. It features a hybrid architecture combining Gated DeltaNet linear attention and standard Gated Attention with 256 total experts (8 routed + 1 shared), and includes a vision encoder for image and video understanding. Optimized for agentic coding, long-context reasoning, and visual tasks; supports 256K native context (extensible to ~1M via YaRN) with integrated thinking mode for multi-turn agent interactions.

Qwen3.6-35B-A3B is an open-source model in the Qwen3.6 family. The structured metadata tracks a 262k-token context window, multimodal input, function calling, and tool use. This page tracks provider routes through OpenRouter and Novita AI, with the cheapest tracked route listed at $0.15 input and $1 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 73.4, SWE-bench Pro 49.5, and LiveCodeBench 80.4.

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

Coding

Q/$ C

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ B

1 relevant benchmark 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$0.150$1.00
Serverless
Novita AI$0.248$1.49
Serverless

Capabilities

VisionMultimodalFunction CallingTool Use

Benchmark peer barsfor Coding

Benchmark scores(8)

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.
BenchmarkScoreVersionEvaluationSource
SWE-bench Verified73.4From official model card (resolved)Observed 2026-06-07Source
SWE-bench Pro49.5Observed 2026-04-16Source
LiveCodeBench80.4v6Observed 2026-04-16Source
MMLU PRO85.2From official HuggingFace model card (accuracy)Observed 2026-06-07Source
Google-Proof Q&A86.0diamondObserved 2026-04-16Source
MathVista86.4miniObserved 2026-04-16Source
MMMU Pro75.3LLM-Stats aggregatorObserved 2026-06-07Source
AIME 202692.7AIME 2026 (accuracy)Observed 2026-06-07Source

Migration checks

No linked migration route is available for this model yet.

Compare Qwen3.6-35B-A3B with other models

Show all 36 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has a context window of 262k tokens.

How much does Qwen3.6-35B-A3B cost?

Qwen3.6-35B-A3B pricing ranges from $0.15/1M to $0.248/1M input tokens depending on the provider.

When was Qwen3.6-35B-A3B released?

Qwen3.6-35B-A3B was released on 2026-04-16.

Which providers offer Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B is available from 2 providers: OpenRouter, Novita AI.

What benchmarks has Qwen3.6-35B-A3B been tested on?

Qwen3.6-35B-A3B has been evaluated on 8 benchmarks, including SWE-bench Verified, SWE-bench Pro, LiveCodeBench, MMLU PRO, Google-Proof Q&A.