Contamination Map Methodology

Text / LLM / Model

Qwen3.8-Flash-Next

Organisation
Alibaba Cloud (Qwen Team)
Family
Qwen · version 3.8-Flash-Next
Released
2026-08-24 (Hugging Face repo creation of Qwen/Qwen3.8-Flash-Next (API createdAt), https://huggingface.co/api/models/Qwen/Qwen3.8-Flash-Next)
Checkpoints
Qwen/Qwen3.8-Flash-Next
Weights
Open · custom 'qwen-community-1.0' license
Links
PaperModel cardCode

Training data disclosure: None

Level determined for 0% of benchmark cells.

Benchmark cells

Classic LLM benchmarks

Unknown MMLU (Measuring Massive Multitask Language Understanding) · training data not disclosed in enough detail

Unknown GSM8K (Grade School Math 8K) · training data not disclosed in enough detail

Unknown MATH (Mathematics Aptitude Test of Heuristics) · training data not disclosed in enough detail

Unknown HumanEval · training data not disclosed in enough detail

Unknown ARC-Challenge (AI2 Reasoning Challenge, Challenge Set) · training data not disclosed in enough detail

Unknown HellaSwag · training data not disclosed in enough detail

Unknown TruthfulQA · training data not disclosed in enough detail

Unknown WinoGrande · training data not disclosed in enough detail

Recent LLM benchmarks

Unknown GPQA Diamond · training data not disclosed in enough detail

Unknown MMLU-Pro · training data not disclosed in enough detail

Unknown LiveCodeBench (code generation, release_v6) · training data not disclosed in enough detail

Unknown SWE-bench Verified · training data not disclosed in enough detail

Unknown AIME 2024 · training data not disclosed in enough detail

Unknown AIME 2025 · training data not disclosed in enough detail

Unknown MATH-500 · training data not disclosed in enough detail

Notes

The technical report covers architecture (hybrid attention, gated residual, n-gram embedding layer) and gives no description of training data, cutoff or decontamination.

Sources