Qwen3.8 27B Benchmarks, Pricing & Rankings
Alibaba · 2026-09-01 · Open · Current
Snapshot 2026-10-14 · updated weekly
Qwen3.8 27B ranks #29 of 42 on the AMR leaderboard.
Qwen3.8 27B benchmark scores
| GPQA Diamond | 76.8% | |
| MMLU-Pro | 75.1% | |
| SWE-Bench Verified | 50.4% | |
| AIME 2025 | 73.9% | |
| LiveCodeBench v6 | 64.8% | |
| Arena Elo | 1352 |
Qwen3.8 27B price, speed & context
Input price
$0.15
per 1M tokens
Output price
$0.60
per 1M tokens
Speed
186
tok/s
Context
256K
tokens
About Qwen3.8 27B
Qwen3.8 27B is the dense open workhorse of the Qwen line — the most self-hosted open model class of 2026, single-GPU deployable.
Models around Qwen3.8 27B in the rankings
More Alibaba models
Qwen3.8 27B FAQ
Where does Qwen3.8 27B rank?
Qwen3.8 27B ranks #29 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 79.8. Its strongest dimension is GPQA Diamond at 76.8%.
How much does Qwen3.8 27B cost?
Qwen3.8 27B costs $0.15 per million input tokens and $0.60 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.49 per million tokens.
What is the Qwen3.8 27B context window?
Qwen3.8 27B supports a 256K token context window and generates at a median 186 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is Qwen3.8 27B open source?
Yes — Qwen3.8 27B ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Qwen3.8 27B?
Gemini 3.1 Pro ranks one place higher at #28 with an AMR score of 80.2. Qwen3.8 27B still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.