Qwen3 8B Base
Alibaba · 2025-04-29 · 8.2B parameters
Qwen3-8B-Base is the pre-trained (not instruction-tuned) 8B dense checkpoint of Alibaba's Qwen3 family, released April 29, 2025 under Apache 2.0 alongside the post-trained Qwen3-8B. Qwen describes a three-stage pre-training on about 36 trillion tokens in 119 languages, ending with long-context training at 32,768 tokens, which is the checkpoint's configured context length.
Benchmark scores
| Benchmark | Score |
|---|---|
| BBH (BIG-Bench Hard) | 78.4 |
| Capability | 116.7 |
| GSM8K | 89.8 |
| MATH | 60.8 |
| MGSM | 76.0 |
| MMLU | 76.9 |
| MMLU Pro | 56.7 |
| MMLU-Redux | 76.2 |
| SuperGPQA | 31.6 |