llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen3.6 35B A3B

Alibaba Cloud / Qwen Team model product

Qwen3.6 35B A3B

Qwen3.6-35B-A3B is the first open-weight variant of the Qwen3.6 series, a multimodal Mixture-of-Experts model with 35B total parameters and 3B activated. It pairs a vision encoder with a hybrid 40-layer language model that interleaves Gated DeltaNet linear-attention blocks and Gated Attention blocks (10 × (3 × DeltaNet + 1 × Attention)) over 256 experts (8 routed + 1 shared, expert dim 512). The release prioritizes stability and real-world utility, with substantial gains in agentic coding (frontend workflows, repo-level reasoning) and a new option to preserve reasoning context across turns. Native context length is 262K tokens, extensible to ~1M via YaRN, and the model thinks by default.

Updated Aug 10, 2026. Default version: Qwen3.6-35B-A3B

Compare
LLMBoard score48.2Qwen3.6-35B-A3B
Coverage80%11 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen3.6-35B-A3B
Released
Apr 16, 2026
Knowledge cutoff
Unknown
Parameters
35B
Context window
262.1K
Max output
65.5K
Inputs
audio, image, text, video
Outputs
text
Open weights
Yes
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen3.6-35B-A3B category scores

Benchmark results

Published benchmark records for the scored version Qwen3.6-35B-A3B.

49 rows
Columns

Show columns

Hallusion Bench0.721693.3%CAug 7, 2026
MMBench-V1.10.921894.1%CAug 7, 2026
CC-OCR0.831888.2%CAug 7, 2026
ODinW0.531686.7%CAug 7, 2026
ZEROBench-Sub0.33550.0%CAug 7, 2026
DeepPlanning0.34962.5%CAug 7, 2026
EmbSpatialBench0.84857.1%CAug 7, 2026
OmniDocBench 1.50.941680.0%CAug 7, 2026
RefCOCO-avg0.94750.0%CAug 7, 2026
TAU3-Bench0.74525.0%CAug 7, 2026
VideoMME w/o sub.0.841066.7%CAug 7, 2026
ZClawBench0.5440.0%CAug 7, 2026
MathVista-Mini0.952381.8%CAug 7, 2026
MLVU0.951055.6%CAug 7, 2026
MVBench0.751775.0%CAug 7, 2026
RefSpatialBench0.65620.0%CAug 7, 2026
RealWorldQA0.962680.0%CAug 7, 2026
VITA-Bench0.461044.4%CAug 7, 2026
SkillsBench0.3770.0%CAug 7, 2026
VideoMME w sub.0.971033.3%CAug 7, 2026
AI2D0.983277.4%CAug 7, 2026
AIME 20260.981756.3%CAug 7, 2026
MCP-Mark0.4880.0%CAug 7, 2026
WideSearch0.68912.5%CAug 7, 2026
C-Eval0.991852.9%CAug 7, 2026
HMMT250.992566.7%CAug 7, 2026
LVBench0.792465.2%CAug 7, 2026
HMMT Feb 260.8101110.0%CAug 7, 2026
SimpleVQA0.6101325.0%CAug 7, 2026
MMMU0.8116383.9%CAug 7, 2026
VideoMMMU0.8112660.0%CAug 7, 2026
MMLU-Redux0.9124876.6%CAug 7, 2026
SuperGPQA0.6123466.7%CAug 7, 2026
Claw-Eval0.513130.0%CAug 7, 2026
NL2Repo0.314140.0%CAug 7, 2026
HMMT 20250.9163353.1%CAug 7, 2026
IMO-AnswerBench0.8161916.7%CAug 7, 2026
MMLU-Pro0.91612988.3%CAug 7, 2026
LiveCodeBench v60.8205363.5%CAug 7, 2026
MCP Atlas0.6223027.6%CAug 7, 2026
SWE-bench Multilingual0.7223436.4%CAug 7, 2026
CharXiv-R0.8244750.0%CAug 7, 2026
Toolathlon0.331310.0%CAug 7, 2026
MMMU-Pro0.8326551.6%CAug 7, 2026
Terminal-Bench 2.00.5334933.3%CAug 7, 2026
SWE-Bench Pro0.543442.3%CAug 7, 2026
SWE-Bench Verified0.74410458.3%CAug 7, 2026
GPQA0.94723380.2%CAug 7, 2026
Humanity's Last Exam0.2579238.5%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.167 input, $0.557 output per 1M via Cortecs
Tracked offerings
5
5 rows
Columns

Show columns

QVACqwen3.6-35b-a3bglobalN/AN/A262.1KAug 7, 2026
Cortecsqwen3.6-35b-a3bglobal$0.167$0.557262KAug 7, 2026
LLM Gatewayqwen3.6-35b-a3bglobal$0.248$1.49262.1KAug 7, 2026
Scalewayqwen3.6-35b-a3bglobal$0.25$1.5128KAug 7, 2026
GreenPTqwen3.6-35b-a3bglobal$0.342$2.05262.1KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Qwen3.6 35B A3B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Qwen3.6-35B-A3BApr 16, 202648.235B262.1K65.5KYesApache 2.0

What is Qwen3.6 35B A3B?

A concise description based on the published model registry.

Qwen3.6-35B-A3B is the first open-weight variant of the Qwen3.6 series, a multimodal Mixture-of-Experts model with 35B total parameters and 3B activated. It pairs a vision encoder with a hybrid 40-layer language model that interleaves Gated DeltaNet linear-attention blocks and Gated Attention blocks (10 × (3 × DeltaNet + 1 × Attention)) over 256 experts (8 routed + 1 shared, expert dim 512). The release prioritizes stability and real-world utility, with substantial gains in agentic coding (frontend workflows, repo-level reasoning) and a new option to preserve reasoning context across turns. Native context length is 262K tokens, extensible to ~1M via YaRN, and the model thinks by default.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen3.6 35B A3B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen3.6 35B A3BvsGemini 1.5 ProQwen3.6 35B A3BvsLlama 4 MaverickQwen3.6 35B A3BvsMiniMax M1 40KQwen3.6 35B A3BvsGemma 4 12BQwen3.6 35B A3BvsPhi 4 ReasoningQwen3.6 35B A3BvsGemma 2 27B

Models similar to Qwen3.6 35B A3B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#86+0.9
AC

Qwen3 235B A22B

Alibaba Cloud / Qwen Team

49.0 LLMBoard

DetailsCompare
#95-2.8
AC

Qwen2.5 Coder 32B

Alibaba Cloud / Qwen Team

45.4 LLMBoard

DetailsCompare
#79+3.4
AC

Qwen2.5 VL 32B

Alibaba Cloud / Qwen Team

51.5 LLMBoard

DetailsCompare
#78+3.5
AC

Qwen3 VL 32B Thinking

Alibaba Cloud / Qwen Team

51.7 LLMBoard

DetailsCompare
#102-4.3
AC

Qwen2.5 14B

Alibaba Cloud / Qwen Team

43.9 LLMBoard

DetailsCompare
#72+4.9
AC

Qwen2.5 72B

Alibaba Cloud / Qwen Team

53.1 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen3.6 35B A3B.

When was Qwen3.6 35B A3B released?

Qwen3.6 35B A3B's default version was released on Apr 16, 2026.

How much does Qwen3.6 35B A3B cost?

No official standard PAYG price is currently available for Qwen3.6 35B A3B. The lowest tracked third-party offer starts at $0.167 input and $0.557 output via Cortecs.

Who created Qwen3.6 35B A3B?

Qwen3.6 35B A3B is published under Alibaba Cloud / Qwen Team in the model registry.

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

The default version has a 262.1K token context window.

Is Qwen3.6 35B A3B open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Qwen3.6 35B A3B?

5 published provider offerings are linked to the default version.

What models should I compare Qwen3.6 35B A3B with?

Nearby ranked alternatives include Gemini 1.5 Pro, Llama 4 Maverick, MiniMax M1 40K.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai