> Qwen3.8-27B is an open-weights AI model from Alibaba, released 14 Aug 2026. Index score 152 (GPT-4 = 100), rank 55 of 229 ranked models. API price $0.42 in / $3.0 out per million tokens, 1M context. [Models](https://themodelindex.org/models/) /[Alibaba](https://themodelindex.org/labs/alibaba/) # Qwen3.8-27B Alibaba Released 14 Aug 2026 Open [Compare](https://themodelindex.org/compare/qwen3-8-27b-vs-gpt-6-astra/) [Run it yourself →](https://themodelindex.org/local/) [Announcement](https://qwen.ai/blog?id=qwen3.8-flash-next&ref=upstract.com) 152140–164 Index score #55 · provisional, limited data 0/ 8 Core tests taken 0 of 6 areas · plus 4 anchor tests −35 Versus the frontier at release best then: Claude Opus 5 $0.42/ $3.0 Price per million tokens input / output, list price 1M Context window tokens it reads at once ## Where it sits · on the frontier _Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_ GPT-5 reached this score 12 months earlier. ## Test results · by area · tick = best by any model Show 3 anchor tests Reasoning & knowledge no evidence yet GPQA Diamond no result Humanity's Last Exam no result Maths evidence FrontierMath T1-3 no result Coding no evidence yet SWE-bench Verified no result Terminal-Bench no result Agents evidence APEX-Agents no result Novel problems no evidence yet ARC-AGI-2 no result Long tasks no 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 say · rank on each leaderboard The Model Index independent tests, our method #55 of 219 · 152 Artificial Analysis Intelligence Index overall capability across ten evaluations #26 of 207 · 34 LMArena · Maths maths questions in chat #58 of 373 · 1458 LMArena · Coding coding questions in chat #61 of 383 · 1505 LMArena · WebDev building web apps and front ends #25 of 123 · 1590 LMArena · Text overall chat quality, judged by people #86 of 388 · 1439 Epoch Capabilities Index overall capability from many benchmarks #53 of 239 · 149.4 LMArena · Vision understanding images #51 of 149 · 1242 LMArena · Creative writing creative writing #144 of 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 at · top 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 it · prices checked 1 Oct 2026 #### From the lab Qwen Chat app · subscription ↗ Alibaba Cloud Model Studio API ↗ #### API providers · 16 · per million tokens, in / out P Phala $0.15 / $1.88 cheapest D DeepInfra $0.15 / $1.88 · bf16 ↗ D Darkbloom $0.050 / $2.2 · fp4 ↗ A AkashML $0.20 / $1.78 · fp8 ↗ I Ionstream $0.089 / $2.55 · fp8 ↗ P Parasail $0.24 / $2.2 · fp8 ↗ C Chutes $0.24 / $2.2 · fp8 ↗ M Mancer 2 $0.20 / $2.5 · fp8 ↗ #### Run it yourself 🤗 Official weights Qwen/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 Released 14 Aug 2026 Announcement [qwen.ai ↗](https://qwen.ai/blog?id=qwen3.8-flash-next&ref=upstract.com) Release entry Qwen3.8-27B Scored as Qwen 3.8 27B Artificial Analysis index 34 · xhigh Output speed 45 tokens/s Hugging Face [Qwen/Qwen3.8-27B ↗](https://huggingface.co/Qwen/Qwen3.8-27B) ## Alibaba releases · around this one Qwen3.8-Max Closed 3 AUG 2026 index 170 Qwen3.8-2.4T-A95B Open 12 AUG 2026 ~169 est. Qwen3.8-27B Open 14 AUG 2026 index 152 Qwen3.8-Flash-Next Open 24 AUG 2026 ~169 est. Qwen3.8-Flash Closed 26 AUG 2026 --- Source: https://themodelindex.org/models/qwen3-8-27b/ · The Model Index · data as of 2026-10-01