Qwen3.8 Next Benchmarks, Pricing & Rankings
Alibaba · 2026-09-16 · Open · Current
Snapshot 2026-10-14 · updated weekly
Qwen3.8 Next ranks #23 of 42 on the AMR leaderboard.
Qwen3.8 Next benchmark scores
| GPQA Diamond | 82.9% | |
| MMLU-Pro | 81.8% | |
| SWE-Bench Verified | 61.9% | |
| AIME 2025 | 82.4% | |
| LiveCodeBench v6 | 71.2% | |
| Arena Elo | 1382 |
Qwen3.8 Next price, speed & context
Input price
$0.50
per 1M tokens
Output price
$1.80
per 1M tokens
Speed
104
tok/s
Context
512K
tokens
About Qwen3.8 Next
Qwen3.8 Next is Alibaba’s latest open flagship with native agentic tool-calling and the best multilingual coverage of any open model tracked.
Models around Qwen3.8 Next in the rankings
More Alibaba models
Qwen3.8 Next FAQ
Where does Qwen3.8 Next rank?
Qwen3.8 Next ranks #23 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 83.6. Its strongest dimension is GPQA Diamond at 82.9%.
How much does Qwen3.8 Next cost?
Qwen3.8 Next costs $0.50 per million input tokens and $1.80 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $1.48 per million tokens.
What is the Qwen3.8 Next context window?
Qwen3.8 Next supports a 512K token context window and generates at a median 104 output tokens per second. That context fits roughly 341 standard documents in a single prompt.
Is Qwen3.8 Next open source?
Yes — Qwen3.8 Next ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Qwen3.8 Next?
GLM-5.3 Flash ranks one place higher at #22 with an AMR score of 84.1. Qwen3.8 Next still wins 6 of the tracked dimensions head-to-head — check the comparison table to see exactly which.