Qwen3.5-122B-A10B

Released
2026-02-24
Last refreshed
2026-10-09
Status
Researched 155d ago
Open sourceCommercial use: permittedMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use
Alibaba releases · 51 in the last 12 months · this family litChangelog →
Specifications
Family
Qwen3.5
Released
2026-02-24
Context
256K
Parameters
122B
Architecture
Mixture of Experts
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Created by
Alibaba

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$2.08
Input / 1M
$0.260

Cheapest of 3 routes · Alibaba Cloud PAI-EAS

Providers(3)
OpenRouterAlibaba Cloud PAI-EASNovita AI
View 3 provider routes
Links
Website HuggingFace

About

Open-weight MoE Qwen3.5 model with 122B total and 10B active parameters. Apache 2.0.

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Alibaba Cloud PAI-EAS$0.260$2.08
Serverless
OpenRouter$0.260$2.08
Serverless
Novita AI$0.400$3.20
Serverless

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

SWE-bench VerifiedRank 64 of 99
Claude Fable 5
96.0
Claude Opus 5
96.0
Claude Mythos Preview
93.9
Claude Opus 4.8
88.6
Qwen3.5-122B-A10Bcurrent
72.0
LiveCodeBenchRank 38 of 73
DeepSeek V4 Pro
93.5
Gemini 3.1 Pro Preview
91.7
DeepSeek V4 Flash
91.6
Qwen3.7-Max
91.6
Qwen3.5-122B-A10Bcurrent
78.9

Benchmark scores(10)

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
Google-Proof Q&A85.7diamondObserved 2026-04-18—Source
MMMU Pro76.9LLM-Stats aggregatorObserved 2026-06-07—Source
Berkeley Function Calling Leaderboard v372.2BFCL-V4, from official model card (accuracy)Observed 2026-06-07—Source
BrowseComp63.8BrowseComp (accuracy%)Observed 2026-06-07—Source
Humanity's Last Exam25.3HLE with CoT, no tools, from official model card (accuracy)Observed 2026-06-07—Source
LiveCodeBench78.9LiveCodeBench v6 (pass@1)Observed 2026-06-07—Source
MMLU PRO86.7From official HuggingFace model card (accuracy)Observed 2026-06-07—Source
MultiChallenge61.5Multi-Challenge leaderboard rank 7 of 28 (accuracy%)Observed 2026-06-07—Source
SWE-bench Verified72.0From official model card (resolved)Observed 2026-06-07—Source
τ-bench79.5TAU2-Bench, from official model card (accuracy)Observed 2026-06-07—Source

Migration checks

No linked migration route is available for this model yet.

Compare Qwen3.5-122B-A10B with other models

Show all 18 popular comparisonssorted by 7-day search impressions
Qwen3.5-122B-A10B vs GLM-516Qwen3.5-122B-A10B vs DeepSeek R114Qwen3.5-122B-A10B vs Claude Opus 4.512Qwen3.5-122B-A10B vs DeepSeek R1 052812Qwen3.5-122B-A10B vs Gemini 2.5 Pro10Qwen3.5-122B-A10B vs Gemini 2.5 Flash10Qwen3.5-122B-A10B vs Claude Opus 4.69Qwen3.5-122B-A10B vs Mistral Large 29Qwen3.5-122B-A10B vs Grok 3 Mini9Qwen3.5-122B-A10B vs Llama 3.2 1B Instruct8Qwen3.5-122B-A10B vs Mistral Nemotron6Qwen3.5-122B-A10B vs GPT-5.45Qwen3.5-122B-A10B vs GPT-5.25Qwen3.5-122B-A10B vs Kimi K2.54Qwen3.5-122B-A10B vs GLM-5 Turbo3Qwen3.5-122B-A10B vs o33Qwen3.5-122B-A10B vs o3 Mini1Qwen3.5-122B-A10B vs Mixtral 8x7B0