Skip to content

Alibaba · Chat

Qwen 3.8 27B

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.
From Cloudflare Workers AI's listing:
Qwen 3.8 27B is a 27-billion-parameter instruction-tuned language model from Alibaba's Qwen family, designed for vision, efficient general-purpose text generation and agentic workloads.
llminfo IQ
129.4
Maker's price
$1.125 blended / 1M
Max context
1.1M
Listings
238

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/Qwen3.8-27B Model architecture, as its sources state it llminfo IQ 129.4, ranked among chat models. From 251 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 111.4, 95% interval 104–119. From 23 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 computedPoor value (39.7). Costs more per task than its benchmark results predict. From 30 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 5 Aug 2026Maker HQ: CN (source)
All rankings: #22 in Google Trends interest this week #35 on OpenRouter this month #38 on OpenRouter this week #39 on OpenRouter today #109 on NanoGPT recentlyAll rankings: #22 in Google Trends interest this week #35 on OpenRouter this month #38 on OpenRouter this week #39 on OpenRouter today #109 on NanoGPT recentlySources: LMArena data, Cloudflare Workers AI, EmpirioLabs data, flex.ai API data, Models.dev data, Hugging FacePrimary data from LMArena from Cloudflare Workers AI: architecture, description from EmpirioLabs: primary mode from flex.ai API: hugging face id from Models.dev: weights availability from Hugging Face: release date
Tags from its sources:instructreasoningtoolsvisionopen-sourcemultimodalvideocodingagenticlong-context

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 1 of the 9 peers that say either way has open weights.

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
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Alibaba CloudRegions: 🇸🇬🇨🇳 ap-southeast-1, cn-beijingqwen3.8-27bSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud QwenNot published by the provider$0.50$3.00——
 Flowdotqwen/qwen3.8-27b:free · freeSource: FlowDot data262K$0.00$0.00——
 NanoGPTInference by AoruRegions: 🇰🇷 KRqwen/qwen3.8-27b · NVFP4Source: NanoGPTNot published by the provider$0.105cache read $0.0525$0.63——
 Paraloncloudqwen3.8-27bSource: Models.dev data131K$0.12$1.70——
 Hugging FaceInference by MancerQwen/Qwen3.8-27BSource: Hugging Face Inference Providers data262K$0.125$1.50——
 Mancerqwen38-27b · fp8Source: Mancer data262K$0.125$1.50——
 Fastrouterqwen/qwen3.8-27bSource: FastRouter data262K$0.15cache read $0.0375$1.875——
 OpenRouterInference by DeepInfraqwen/qwen3.8-27b · fp8Source: OpenRouter data docs262K$0.15cache read $0.0375$1.87523705ms
 Akiqwen3.8-27bSources: AKI data, Models.dev data262K$0.15cache read $0.075$0.65——
 TenstorrentQwen/Qwen3.8-27BSource: Models.dev data262K$0.15cache read $0.05$2.00——

22 listings without a price are hidden.

Via subscription

Included in a provider's subscription rather than sold per token. See the plan for what it includes.

Included in plans

Yolo-Auto BuilderYolo AutoSubscription$19/moPlan page
Yolo-Auto ProYolo AutoSubscription$39/moPlan page
Yolo-Auto FleetYolo AutoSubscription$99/moPlan page

Benchmarks

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

Multilingual

Bangla LLM BenchSource: Bangla LLM Bench data docs
EKI EstonianSource: Keelemudelite mõõdupuu data docs · Aug 2026
IdrockBench Uzbek4 related benchmarks · 4 results
NepNewsBench v2 draft40 related benchmarks · 40 results
entity F1 (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
core fact recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
core fact recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
core fact recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
coverage precision proxy (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
Show 34 more resultsHide 34 results
effective score (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
effective score (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
effective score (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
English prose quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity F1 (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity F1 (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity precision (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity precision (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity precision (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
entity recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
Nepali prose quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
Nepali prose quality (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
supporting fact recall (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
supporting fact recall (English-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
supporting fact recall (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
valid-answer quality (all questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off
valid-answer quality (Nepali-source questions)
Source: NepNewsBench v2 (draft candidate release) data · Sep 2026
Alibaba via openrouter, reasoning off

Human preference

Arena ELO57 related benchmarks · 57 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 53 more benchmarksHide 53 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 - 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 - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled

Agentic

Agents' Last Exam3 related benchmarks · 3 results
Agents' Last Exam
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Overall Score
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · Overall Score
Pass Rate
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · Pass@1
AndroidWorld3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B 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
Arena AgentSource: LMArena data
GAIA4 results
Source: GAIA Leaderboard data · Sep 2026
Difficulty level
Difficulty not reported
JobBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B 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.
Qwen3.8-27B 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 Pro3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Code · temp 1.0 · top_p 0.95 · 256K · refined tasks;Claude 对照为官方值
Qwen3.8-27B model card · Claude Code · temp 1.0 · top_p 0.95 · 256K · corrected/refined tasks
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: OpenRouter benchmark exports
14 Aug 2026 version · 90-day results
Across 25 providers lowest 70.5% median 76% highest 78.7%OpenRouter's automatic routing 76.7%
Show results from 25 providers and OpenRouter's automatic routingHide results from 25 providers and OpenRouter's automatic routing
  • SiliconFlow
  • PrimeIntellect
  • Near AI
  • DekaLLM
  • ModelRun
  • DeepInfra
  • OpenRouter's automatic routing
  • Nebius
  • AkashML
  • Cloudflare
  • Chutes
  • Reka
  • Parasail
  • Mancer 2
  • Io Net
  • Novita
  • Ionstream
  • Cerebras
  • CoreWeave
  • Darkbloom
  • Modal
  • Alibaba
  • Wafer
  • Phala
  • Venice
  • Tenstorrent
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · official WebArena grader · OSWorld scaffold
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

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.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B 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
NL2RepoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
QwenSWEBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B 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-MM4 related benchmarks · 5 results
SWE-MM
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-bench Multilingual
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
mini-SWE-agent · temp 1.0 · top_p 0.95 · 256K
SWE-bench Multimodal
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · Claude Code · public dev split · Opus 4.7 System Card Appendix 8.3 modifications
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench-Live MultiLang Go
Source: SWE-bench-Live leaderboard data · Oct 2026
scaffold: ami-agent, set: go, instances: 138
ValsSource: Vals AI
Vision2Web3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Frontend/Webpage/Website 平均 · Claude Code · gpt-5.4-2026-03-05 judge
Qwen3.8-27B model card · frontend/webpage/website average · Claude Code · gpt-5.4-2026-03-05 judge
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond31 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B model card · published setting
Source: OpenRouter benchmark exports
14 Aug 2026 version · 90-day results
Across 28 providers lowest 75.7% median 82.7% highest 87.2%OpenRouter's automatic routing 82.2%
Show results from 28 providers and OpenRouter's automatic routingHide results from 28 providers and OpenRouter's automatic routing
  • Morph
  • Cloudflare
  • StreamLake
  • Modal
  • DekaLLM
  • DeepInfra
  • SiliconFlow
  • Alibaba
  • Cerebras
  • PrimeIntellect
  • Parasail
  • Wafer
  • Ionstream
  • AkashML
  • Novita
  • CoreWeave
  • Chutes
  • Nebius
  • OpenRouter's automatic routing
  • GMICloud
  • Mancer 2
  • Darkbloom
  • Tenstorrent
  • Near AI
  • Io Net
  • ModelRun
  • Venice
  • Reka
  • Phala

Reasoning

CoWorkBench3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B 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
ERQA3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B 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.
Qwen3.8-27B 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

General

Long context

Vision

CharXiv-R3 related benchmarks · 5 results
CharXiv-R
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CharXiv (RQ) · With CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
with Code Interpreter
CharXiv (RQ) · Without CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
without Code Interpreter
LVBenchQwen3.8 Omni Flash 官方发布表 · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RealWorldQA3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B 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

MathVision3 related benchmarks · 5 results
MathVision
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
With CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · with Code Interpreter
With Code Interpreter
Without CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-27B model card · without Code Interpreter
Without Code Interpreter · Qwen 固定 boxed prompt;其他模型取有/无 boxed 较高值

Instruction following

IFBench3 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8 Omni Flash 官方发布表
Qwen3.8-27B 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

OCR

Other

BabyVision · With CIQwen3.8-27B 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 CIQwen3.8-27B 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.
BlenderWorld15 related benchmarks · 15 results
Art & Animation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 30 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Architecture & Interiors
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 72 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Characters & Animals
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 25 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Fully satisfied rubric
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Image/video-input overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 145 image or video reference tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Nature & Landscapes
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 21 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Show 9 more resultsHide 9 results
Overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Procedural & Game Assets
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 10 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Products & Manufacturing
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 28 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Rendering & Simulation
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 17 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Science & Visualization
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 9 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Text-only overall score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 78 text-only tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Vehicles & Machinery
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 11 category tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Visual-quality dimension score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Weighted rubric score
Reported by BlenderWorld authors / Alibaba Token Hub · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
benchmark-owner paper run · 223 tasks · Blender 4.2.10 / Blender MCP paper setup · GPT-5.6 Terra main judge · generation-agent harness and reasoning effort not stated on public leaderboard
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ClawEval multimodal split · 三次运行平均分
Qwen3.8-27B model card · mean score across three trials
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ClawEval multimodal split · 三次运行中至少一次通过
Qwen3.8-27B model card · Pass@3 · at least one pass in three trials
DeepSWE v1.12 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Code / mini-SWE-agent 取较高值 · temp 1.0 · top_p 0.95 · 256K
Qwen3.8-27B model card · published setting
NL2Repo-Bench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claude Code · 禁止访问目标仓库的 Bash 命令
Qwen3.8-27B model card · published setting
SkillsBench · Vals6 related benchmarks · 6 results
With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=alibaba/qwen3.8-27b · provider=Alibaba · reasoning_effort=xhigh · temperature=1 · top_p=0.95 · max_output_tokens=65536
WildClawBench5 related benchmarks · 5 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 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. · Data by LLM Stats · 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) · Bangla LLM Bench, Md Deluair Hossen. Source tasks: Hendrycks et al. 2021 (MMLU), OpenAI MMMLU, Bandarkar et al. 2024 (Belebele), Shi et al. 2023 (MGSM), Nahin et al. 2025 (TituLLMs). Public numeric community results; results licence not separately stated. · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · IdrockBench, IDROCK AI Excellence Center, New Uzbekistan University. Public numeric results; no results licence stated (code MIT and dataset licences not borrowed). · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here. · SWE-bench-Live (Microsoft and contributors), swe-bench-live.github.io. Resolve rates computed from the published report counts. · 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: @cf/qwen/qwen3.8-27b, alibaba/qwen3.8-27b, bailian/qwen3.8-27b, cerebras/qwen-3.8-27b, deepinfra/qwen/qwen3.8-27b, e2ee-qwen-3.8-27b, empiriolabs/qwen3-8-27b, gmi/qwen/qwen3.8-27b, groq/qwen/qwen3.8-27b, hf:qwen/qwen3.8-27b, nebius/qwen/qwen3.8-27b, novita/qwen3.8-27b, parasail-qwen38-27b, phala/qwen3.8-27b, qwen 3.8 27b, qwen-3-8-27b, qwen-3.8-27b, qwen-3.8-27b-flex, qwen-3.8-27b-nvfp4, qwen/qwen3.8-27b, qwen/qwen3.8-27b-fp8, qwen/qwen3.8-27b-tee, qwen/qwen3.8-27b:batch, qwen/qwen3.8-27b:free, qwen/qwen3.8-27b:thinking, qwen3-8-27b, qwen3.8-27b-4bit-mtp, qwen3.8-27b-fast, qwen3.8-27b-fp8, qwen38-27b, streamlake/qwen3.8-27b, tee/qwen3.8-27b, wandb/qwen/qwen3.8-27b

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