Skip to content

Alibaba · Chat

Qwen3.5 397B A17B

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (18 Jan 2027). Plans can change.
From Empiriolabs's listing:
Qwen3.5 397B-A17B is a flagship multimodal reasoning model for language, code, agents, GUI tasks, and image and video understanding.
llminfo IQ
130.6
Maker's price
$1.35 blended / 1M
Max context
262K
Listings
99

Evidence and sources

International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).

🤗 Qwen/Qwen3.5-397B-A17B Model architecture, as its sources state it llminfo IQ 130.6, ranked among chat models. From 367 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 104.8, 95% interval 98–112. From 11 benchmark families across 6 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedFair value (48.4). Costs per task about what its benchmark results predict. From 18 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (46 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 10,516 output tokens per task at default effort.How the Yap score worksReleased 16 Feb 2026Maker HQ: CN (source)
All rankings: #8 in Wikipedia pageviews this week #17 in Bluesky discussions this week #101 on NanoGPT recently #157 on OpenRouter today #168 on OpenRouter this week #184 on OpenRouter this monthAll rankings: #8 in Wikipedia pageviews this week #17 in Bluesky discussions this week #101 on NanoGPT recently #157 on OpenRouter today #168 on OpenRouter this week #184 on OpenRouter this monthSources: LMArena data, DeepInfra data, EmpirioLabs data, Models.dev data, Morpheus Inference Marketplace data, Hugging FacePrimary data from LMArena from DeepInfra: name from EmpirioLabs: primary mode, deprecation date, description from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from Hugging Face: release date
Tags from its sources:instructreasoningtoolsopen-sourcemoecodingagenticvisionfunction-calling

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 18 Jan 2027, within the next 180 days.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Images
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Alibaba CloudRegions: 🇸🇬🇨🇳+2 ap-southeast-1, cn-beijing, eu-central-1, us-east-1qwen3.5-397b-a17bSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, Models.dev data262K$0.60$3.60
 Unorouterqwen3.5-397b-a17b:free · freeSource: Models.dev data262K$0.00$0.00
 Aihubmixqwen3.5-397b-a17bSources: AIHubMix data docs, LiteLLM data262K$0.1644$0.9864
 Alibaba Cloud (China)qwen3.5-397b-a17bSource: Models.dev data262K$0.172$1.032
 Empiriolabsqwen3-5-397b-a17bSources: EmpirioLabs data, LiteLLM data258K$0.172>128k $0.43$1.032>128k $2.58
 Merge Gatewayqwen/qwen3.5-397b-a17bSource: Models.dev data131K$0.172cache read $0.0344$1.032
 Orcarouterqwen/qwen3.5-397b-a17bSource: Models.dev data262K$0.172$1.032
 Baiduqwen3.5-397b-a17bSource: Baidu QianfanNot published by the provider
 Ppioqwen/qwen3.5-397b-a17bSource: PPIO data262K
 Qiniuqwen3.5-397b-a17bSources: Models.dev data, Qiniu AI data, Qiniu AI Model Plaza Pricing256K

9 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO63 related benchmarks · 63 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 59 more benchmarksHide 59 benchmarks
BenchmarkScore
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Captioning
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Entity Recognition
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Agentic

AndroidWorldQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
BFCL-V42 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
BrowseComp3 results
Source: Steel.dev Agent Leaderboards data · Feb 2026
Setting not stated
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · discard-all strategy used by DeepSeek-V3.2 and Kimi K2.5
Qwen3.5 release/model card · simple context folding · 256K
BrowseComp-zh2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MCP-MarkSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
OSWorld-VerifiedQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
tau2-bench13 related benchmarks · 22 results
airline
Source: OpenRouter benchmark exports
16 Feb 2026 version · 90-day results
Across 9 providers lowest 73.4% median 77.6% highest 80.3%OpenRouter's automatic routing 79.7%
Show results from 9 providers and OpenRouter's automatic routingHide results from 9 providers and OpenRouter's automatic routing
  • Alibaba
  • Phala
  • DigitalOcean
  • OpenRouter's automatic routing
  • Parasail
  • Venice
  • GMICloud
  • DeepInfra
  • AtlasCloud
  • Novita
v1 airline pass^1
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 airline pass^2
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 airline pass^3
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 airline pass^4
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 retail pass^1
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
Show 7 more resultsHide 7 results
v1 retail pass^2
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 retail pass^3
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 retail pass^4
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 telecom pass^1
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 telecom pass^2
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 telecom pass^3
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled
v1 telecom pass^4
Source: Sierra tau-bench Leaderboard data docs · Feb 2026
submission-qwen3.5-397b-a17b-think_sierra_2026-03-02, usersim-gpt-5.2, effort-enabled

Vision

CharXiv ReasoningQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
EmbSpatialBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HallusionBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HypersimQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
LVBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMBenchEN-DEV-v1.1Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMUQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMU-ProQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMStarQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MVBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
PMC-VQAQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RealWorldQAQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RefCOCO(avg)Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RefSpatialBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SimpleVQAQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SUNRGBDQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Video-MME8 related benchmarks · 17 results
Video-MME
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card
v2
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
v2 - Avg Acc
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
v2 - Capability Consistency
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
v2 - Level 1
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
v2 - Level 2
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
Show 4 more resultsHide 4 results
v2 - Level 3
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
v2 - Reasoning Coherence
Source: Video-MME-v2
w. sub @ 64, instruct
wo sub @ 64, instruct
VideoMMMUQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
VITA-Bench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

DynaMathQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HMMT 20255 related benchmarks · 5 results
HMMT 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT Feb 25
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Hmmt Feb 2026
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT February 2026
Source: OpenEvals Leaderboard data · Reported by the model's developer. The source relaying it did not verify it. · Mar 2026
HMMT Nov 25
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
HMMT25Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MathVisionQwen3.5 release/model card · fixed boxed-answer prompt · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MathVista-MiniQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
PolyMATH2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
We-MathQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Reasoning

C-Eval2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
CountBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepPlanning2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ERQAQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Global PIQA2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
HLE-Verified¹Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
LingoQAQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMVUQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Seal-02 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
t2-benchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Toolathlon VerifiedQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
WideSearch2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · 256K · no context management
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ZEROBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ZEROBench-SubQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Coding

Arena ELOSource: LMArena data · Nov 2026
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SecCodeBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench Verified3 related benchmarks · 5 results
SWE-bench Verified
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench Multilingual
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQA2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GPQA Diamond13 results
Source: OpenEvals Leaderboard data · Reported by the model's developer. The source relaying it did not verify it. · Mar 2026
Setting not stated
Source: OpenRouter benchmark exports
16 Feb 2026 version · 90-day results
Across 10 providers lowest 86.4% median 87.2% highest 88.3%OpenRouter's automatic routing 87.2%
Show results from 10 providers and OpenRouter's automatic routingHide results from 10 providers and OpenRouter's automatic routing
  • Parasail
  • DigitalOcean
  • GMICloud
  • Phala
  • Alibaba
  • OpenRouter's automatic routing
  • AtlasCloud
  • Venice
  • Novita
  • DeepInfra
  • StreamLake
SuperGPQA2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Multilingual

MMMLU2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
WMT24++2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · 55-language average · XCOMET-XXL
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Long context

Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
LongBench v22 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MMLongBench-DocQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Instruction following

IFBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
IFEval2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Knowledge

Include2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: Clinical Benchmarks data docs · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MMLU-Pro3 related benchmarks · 6 results
MMLU-Pro
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MMLU-Redux
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
X
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · 29-language average
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

General

MAXIFE2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · English + multilingual prompts · 23 settings
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
NOVA-632 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.5 release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

OCR

CC-OCRQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OCRBenchQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Factuality

Safety

Other

AI2D_TESTQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
AIME26Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
BabyVision · With CIQwen3.5 release/model card · with Code Interpreter · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
BabyVision · Without CIQwen3.5 release/model card · without Code Interpreter · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claw-Eval v1.1Reported by Claw-Eval · via BenchBoard docs
Horangi36 related benchmarks · 36 results
MCPMark · Version UnspecifiedQwen3.5 release/model card · GitHub MCP v0.30.3 · Playwright responses truncated at 32K · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MLVU(M-Avg)Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.5-397B-A17B: reasoning-enabled
nuScenesQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ODInW13Qwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
PerceptionBench9 related benchmarks · 9 results
Overall accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Attribute accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Comparison accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Contextual integration accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Counting accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Depth and 3D perception accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Show 3 more resultsHide 3 results
Fine-grained recognition accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Localization accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
Visual relation accuracy
Reported by Moonshot AI / PerceptionBench authors · via BenchBoard docs
benchmark-owner evaluation · 3,000 verified questions total · open-ended short answers · unified prompts · highest available reasoning budget; level not specified · main-table result; run count not specified · GPT-oss-120B judge
RNG-Bench12 related benchmarks · 12 results
Duel Elo
Reported by RNG-Bench / InternLM · via BenchBoard docs
Matching Pairs · image · poker theme · 16 games per model
3D Maze Efficiency
Reported by RNG-Bench / InternLM · via BenchBoard docs
successful episodes only · 13×13 · no minimap · mean optimal path 60 steps
3D Maze Explore Rate
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 13×13 · no minimap · mean optimal path 60 steps
3D Maze Game Score
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 13×13 · no minimap · mean optimal path 60 steps
3D Maze Success Rate
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 13×13 · no minimap · mean optimal path 60 steps
3D Maze Wall Collisions
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 13×13 · no minimap · mean optimal path 60 steps
Show 6 more resultsHide 6 results
Duel Score
Reported by RNG-Bench / InternLM · via BenchBoard docs
Matching Pairs · image · poker theme · 16 games per model
Duel Win Rate
Reported by RNG-Bench / InternLM · via BenchBoard docs
Matching Pairs · image · poker theme · 16 games per model
Matching Pairs Invalid Action
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 10×10 · image · noise theme
Matching Pairs Parse Failure
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 10×10 · image · noise theme
Matching Pairs Responses per Score
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 10×10 · image · noise theme
Matching Pairs Score
Reported by RNG-Bench / InternLM · via BenchBoard docs
single-player · 10×10 · image · noise theme
SLAKEQwen3.5 release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
TAU2BenchQwen3.5 release/model card · official setup except airline fixes from Claude Opus 4.5 System Card · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
V* · With CIQwen3.5 release/model card · with Code Interpreter · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
V* · Without CIQwen3.5 release/model card · without Code Interpreter · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
WildClawBench6 related benchmarks · 6 results
WildClawBench
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Multimodal (26 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · multimodal-input split · 26 tasks
Overall
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Pure-text (34 tasks)
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · pure-text split · 34 tasks
Total Cost
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite
Total Elapsed
Reported by WildClawBench / InternLM · via BenchBoard docs
OpenClaw · full 60-task suite

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Hugging Face official benchmark leaderboards; licence varies by benchmark · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Data by LLM Stats · Steel.dev Agent Leaderboards, MIT (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · OpenEvals/leaderboard-data, MIT (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Shaberi v2.1, Shisa.AI, Apache-2.0. GPT-5.1-judge scores only; judges are not comparable. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SpreadsheetBench (Renmin University of China and contributors), spreadsheetbench.github.io. · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted.

Also known as: aihubmix/qwen3.5-397b-a17b, alibaba/qwen3.5-397b-a17b, alibaba/qwen35-397b-a17b, bailian/qwen3.5-397b-a17b, deepinfra/qwen/qwen3.5-397b-a17b, empiriolabs/qwen3-5-397b-a17b, gmi/qwen/qwen3.5-397b-a17b, nebius/qwen/qwen3.5-397b-a17b, novita/qwen/qwen3.5-397b-a17b, novita/qwen35-397b-a17b, parasail-qwen35-397b-a17b, qwen/qwen3.5-397b-a17b, qwen/qwen3.5-397b-a17b-fp8, qwen/qwen3.5-397b-a17b-tee, qwen/qwen3.5-397b-a17b:thinking, qwen3-5-397b-a17b, qwen3.5-397b, qwen3.5-397b-a17b:free, qwen35-397b-a17b, scaleway/qwen/qwen3.5-397b-a17b, streamlake/qwen3.5-397b-a17b, tensormesh/qwen/qwen3.5-397b-a17b-fp8, together_ai/qwen/qwen3.5-397b-a17b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works