Qwen3.8 27B: Release Intelligence, Performance & Price
Model summary
Verbosity
The Qwen3.8 27B release offers 4 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across the 4 models.
- For intelligence, the top model of Qwen3.8 27B is Qwen3.8 27B (Xhigh) at 34.
- For output speed, the fastest model is Qwen3.8 27B (Non-reasoning) at 50 t/s.
- For latency, Qwen3.8 27B (Non-reasoning) at 3.97s offers the lowest time to first answer token.
- For pricing, Qwen3.8 27B (Xhigh) at $1.01 offers the lowest cost per task. Prices vary up to 2.5x across models.
| Input modality | Supports: text, image, and video |
|---|---|
| Output modality | Supports: text |
| Context window | 256k ~384 A4 pages of size 12 Arial font |
| Total parameters | 27B |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, Elo
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Agentic business operations
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
AA-PersonalityBenchNew
Personality Indexes
More from Alibaba
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8 27B (Xhigh) |  Alibaba | 34 | 27B | 256k | $0.5 | 45 |   +6 | ||
| Qwen3.8 27B (Medium) | Alibaba | 28 | 27B | 256k | $0.5 | 48 | | ||
| Qwen3.8 27B (Low) | Alibaba | 26 | 27B | 256k | $0.5 | 49 | | ||
| Qwen3.8 27B (Non-reasoning) | Alibaba | 20 | 27B | 256k | $0.5 | 50 |   +3 |