Skip to content

Alibaba · Chat

Qwen3.6 27B

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (5 Oct 2026).

Newer version: Qwen 3.8 27B. We compared release dates and version names in our catalogue.

From Empiriolabs's listing:
Qwen3.6 27B improves agentic coding, STEM reasoning, spatial vision, OCR, and text, image, and video understanding on 256K context.
llminfo IQ
123.4
Maker's price
$1.35 blended / 1M
Max context
262K
Listings
81

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/Qwen3.6-27B-FP8 Model architecture, as its sources state it llminfo IQ 123.4, ranked among chat models. From 160 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 100.9, 95% interval 95–107. From 14 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 (39.6). Costs more per task than its benchmark results predict. From 13 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 21 Apr 2026Maker HQ: CN (source)
All rankings: #28 in Google Trends interest this week #185 on OpenRouter today #203 on NanoGPT recently #203 on OpenRouter this week #211 on OpenRouter this monthAll rankings: #28 in Google Trends interest this week #185 on OpenRouter today #203 on NanoGPT recently #203 on OpenRouter this week #211 on OpenRouter this monthSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Ambient data, EmpirioLabs data, flex.ai API data, LiteLLM data, Models.dev data, Morpheus Inference Marketplace data, Hugging FacePrimary data from Alibaba Cloud Model Studio (DashScope) Multi-Region API from Ambient: name from EmpirioLabs: primary mode, description from flex.ai API: hugging face id from LiteLLM: deprecation date from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from Hugging Face: release date
Tags from its sources:instructreasoningtoolsvision

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 2 of the 7 peers that say either way have open weights.

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (5 Oct 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

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-beijingqwen3.6-27bSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, Models.dev data262K$0.60$3.60——
 Llmgateway Providersgreenference/qwen3.6-27bSource: Models.dev data16K$0.12$1.08——
 Llmgatewayqwen3.6-27bSource: LLMGateway data16K$0.15$1.35——
 NanoGPTInference by GreenferenceRegions: 🇪🇺 EUqwen/qwen3.6-27b · fp8Source: NanoGPTNot published by the provider$0.1575cache read $0.0788$1.4175——
 OpenRouterInference by Chutesqwen/qwen3.6-27b · fp8Source: OpenRouter data docs262K$0.25cache read $0.025$2.00252,607.5ms
 ChutesQwen/Qwen3.6-27B-TEE · tee · fp8Sources: Chutes data, Models.dev data262K$0.25cache read $0.025$2.00——
 FlexaiRegions: 🇪🇺 euQwen3.6-27B-FP8 · fp8Source: flex.ai API data262K$0.25$2.00——
 SiliconFlowQwen/Qwen3.6-27B · fp8Sources: Models.dev data, SiliconFlow data262K$0.30$3.20——
 Fastrouterqwen/qwen3.6-27bSource: FastRouter data262K$0.32$3.20——
 FlowdotQwen/Qwen3.6-27BSource: FlowDot data262K$0.32$3.20——
Show all 72 listings

Showing 10 of 72: the maker's own listing first, then the cheapest per 1M input tokens from each provider. One listing with a suspiciously low price is in the full list only.

Also sold by Abacus, Aiand, Aihubmix, Ambient, Apertus, Cortecs AI, DeepInfra, Empiriolabs, Featherless AI, Groq, Hugging Face, Ionet, Kilo, Libertai, Melious, Merge Gateway, Nous Portal, Novita AI, Ofox, OVHcloud, Phala, Ppio, Qiniu, Redpill, Siliconflow Cn, Stackit, Streamlake, Tensormesh, Thinking Machines, Venice, Vercel, Wavespeed, Weights & Biases.

9 listings without a price are hidden.

Benchmarks

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

Vision

CharXiv · RQQwen official release table · thinking mode unless benchmark requires otherwise · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
CharXiv-RSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MLVUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMBenchEN-DEV-v1.1Qwen official release table · thinking mode unless benchmark requires otherwise · DEV v1.1 · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMU2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MMMU-Pro2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MMStar2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
MVBench2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
RealWorldQA2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
RefCOCO(avg)2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SimpleVQA2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Video-MMEQwen official release table · thinking mode unless benchmark requires otherwise · with subtitles · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
VideoMMMU2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Coding

Claw-EvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
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
QwenWebBench2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise · internal bilingual front-end benchmark · auto-render + multimodal judge
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-bench Verified6 related benchmarks · 8 results
SWE-bench Verified
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise · internal bash + file-edit scaffold · 200K
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 Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise · internal scaffold · 200K
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

General

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Aug 2026
IdrockBench Uzbek4 related benchmarks · 4 results

Math

DynaMath2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
HMMT 20256 related benchmarks · 6 results
HMMT 2025
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT 2026 Feb
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
HMMT Feb 25
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
HMMT Feb 26
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
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 Nov 25
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
HMMT25Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Reasoning

C-Eval2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
CountBench2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ERQA2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
V*Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
VLMsAreBlind2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Agentic

AndroidWorld2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-Bench Pro2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise · refined public set · internal scaffold · 200K
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
22 Apr 2026 version · 90-day results
Across 8 providers lowest 73.3% median 76.2% highest 81.3%OpenRouter's automatic routing 77.2%
Show results from 8 providers and OpenRouter's automatic routingHide results from 8 providers and OpenRouter's automatic routing
  • CoreWeave
  • Chutes
  • Reka
  • OpenRouter's automatic routing
  • Alibaba
  • Phala
  • DeepInfra
  • Venice
  • SiliconFlow
Terminal-Bench 2.0 · Terminus-2Qwen official release table · thinking mode unless benchmark requires otherwise · Harbor/Terminus-2 · 3h · 32 CPU/48GB · 256K · five-run mean · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond12 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Effort not reported
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: OpenRouter benchmark exports
22 Apr 2026 version · 90-day results
Across 8 providers lowest 81.7% median 84.7% highest 85.5%OpenRouter's automatic routing 84.8%
Show results from 8 providers and OpenRouter's automatic routingHide results from 8 providers and OpenRouter's automatic routing
  • Venice
  • Chutes
  • Alibaba
  • CoreWeave
  • OpenRouter's automatic routing
  • Phala
  • DeepInfra
  • SiliconFlow
  • Reka
SuperGPQA2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Long context

Human preference

Knowledge

MMLU-Pro2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
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-Redux2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

OCR

CC-OCR2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
OCRBench2 results
Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen official release table · thinking mode unless benchmark requires otherwise
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Instruction following

Other

AIME26Qwen official release table · thinking mode unless benchmark requires otherwise · full AIME 2026 I + II · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claw-Eval · AverageQwen official release table · thinking mode unless benchmark requires otherwise · temp .6 · 256K · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claw-Eval · Pass³Qwen official release table · thinking mode unless benchmark requires otherwise · temp .6 · 256K · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MLVU(M-Avg)Qwen official release table · thinking mode unless benchmark requires otherwise · Reported by Alibaba 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/Qwen3.6-27B: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3.6-27B: reasoning-enabled
NL2Repo-BenchQwen official release table · thinking mode unless benchmark requires otherwise · Claude Code · temp 1.0 · top_p .95 · max_turns 900 · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
QwenClawBench · Version UnspecifiedQwen official release table · thinking mode unless benchmark requires otherwise · internal pre-release set · temp .6 · 256K · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SkillsBench · Self-contained subsetQwen official release table · thinking mode unless benchmark requires otherwise · OpenCode · 78 self-contained tasks · five-run average · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
V* · Without CIQwen official release table · thinking mode unless benchmark requires otherwise · official table does not label CI for this row · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ValsSource: Vals AI
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: Hugging Face official benchmark leaderboards; licence varies by benchmark · 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. · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · Data by LLM Stats · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · 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) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · 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) · 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)

Also known as: aihubmix/qwen3.6-27b, alibaba/qwen3.6-27b, bailian/qwen3.6-27b, deepinfra/qwen/qwen3.6-27b, empiriolabs/qwen3-6-27b, greenference/qwen3.6-27b, libertai/qwen3.6-27b, novita/qwen/qwen3.6-27b, qwen 3.6 27b, qwen-3.6-27b, qwen/qwen3.6-27b, qwen/qwen3.6-27b-tee, qwen/qwen3.6-27b:thinking, qwen3-6-27b, qwen3.6-27b-fp8, qwen3.6:27b, streamlake/qwen3.6-27b, tee/qwen3.6-27b, tensormesh/qwen/qwen3.6-27b-fp8, wandb/qwen/qwen3.6-27b

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