Contamination Map Methodology

Text / LLM / Model

Qwen3-2507 (Instruct-2507 / Thinking-2507)

Organisation
Alibaba Cloud (Qwen Team)
Family
Qwen · version 2507
Released
2025-07-21 (Hugging Face repo creation of Qwen/Qwen3-235B-A22B-Instruct-2507 (API createdAt), https://huggingface.co/api/models/Qwen/Qwen3-235B-A22B-Instruct-2507)
Checkpoints
Qwen/Qwen3-235B-A22B-Instruct-2507, Qwen/Qwen3-235B-A22B-Thinking-2507, Qwen/Qwen3-30B-A3B-Instruct-2507, Qwen/Qwen3-30B-A3B-Thinking-2507, Qwen/Qwen3-4B-Instruct-2507, Qwen/Qwen3-4B-Thinking-2507
Weights
Open · Apache 2.0
Links
Model 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

Updated versions of the Qwen3 instruct/thinking models; the cards only state 'Training Stage: Pretraining & Post-training' and point to the Qwen3 blog. No training-data information for the update.

Sources