The Model Index
Models/Alibaba

Qwen3.8-27B

AlibabaReleased 14 Aug 2026Open
CompareRun it yourself →Announcement
152140–164Index score#55 · provisional, limited data
0/ 8Core tests taken0 of 6 areas · plus 4 anchor tests
−35Versus the frontier at releasebest then: Claude Opus 5
$0.42/ $3.0Price per million tokensinput / output, list price
1MContext windowtokens it reads at once

Where it sitson the frontier

GPT-5 reached this score 12 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeno evidence yet
GPQA Diamond
no result
Humanity's Last Exam
no result
Mathsevidence
FrontierMath T1-3
no result
Codingno evidence yet
SWE-bench Verified
no result
Terminal-Bench
no result
Agentsevidence
APEX-Agents
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksno evidence yet
METR time horizon
no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

What others sayrank on each leaderboard

The Model Indexindependent tests, our method#55of 219 · 152
Artificial Analysis Intelligence Indexoverall capability across ten evaluations#26of 207 · 34LMArena · Mathsmaths questions in chat#58of 373 · 1458LMArena · Codingcoding questions in chat#61of 383 · 1505LMArena · WebDevbuilding web apps and front ends#25of 123 · 1590LMArena · Textoverall chat quality, judged by people#86of 388 · 1439Epoch Capabilities Indexoverall capability from many benchmarks#53of 239 · 149.4LMArena · Visionunderstanding images#51of 149 · 1242LMArena · Creative writingcreative writing#144of 386 · 1363

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

Best attop three among current models

Not in the top three among current models on any category we track.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

Where to use itprices checked 1 Oct 2026

From the lab

Qwen Chatapp · subscription↗Alibaba Cloud Model StudioAPI↗

API providers 16 · per million tokens, in / out

PPhala$0.15 / $1.88cheapestDDeepInfra$0.15 / $1.88 · bf16↗DDarkbloom$0.050 / $2.2 · fp4↗AAkashML$0.20 / $1.78 · fp8↗IIonstream$0.089 / $2.55 · fp8↗PParasail$0.24 / $2.2 · fp8↗CChutes$0.24 / $2.2 · fp8↗MMancer 2$0.20 / $2.5 · fp8↗

Run it yourself

🤗Official weightsQwen/Qwen3.8-27B↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

Facts and sources

Released14 Aug 2026
Announcementqwen.ai ↗
Release entryQwen3.8-27B
Scored asQwen 3.8 27B
Artificial Analysis index34 · xhigh
Output speed45 tokens/s

Alibaba releasesaround this one

Qwen3.8-MaxClosed
index 170
Qwen3.8-2.4T-A95BOpen
~169 est.
Qwen3.8-27BOpen
index 152
Qwen3.8-Flash-NextOpen
~169 est.
Qwen3.8-FlashClosed