Qwen2.5-Math series open-sourced with reward model
Qwen upgraded their math-focused LLM series to Qwen2.5-Math, releasing base models (1.5B/7B/72B), instruction-tuned variants, and a mathematical reward model. The models primarily support English and Chinese math problems via chain-of-thought and tool-integrated reasoning.
PUBLISHED2024-09-18
OBSERVED2026-08-11
AGE1y
SOURCES1
- Base models: Qwen2.5-Math-1.5B/7B/72B
- Instruction-tuned models: Qwen2.5-Math-1.5B/7B/72B-Instruct
- Mathematical reward model also open-sourced
- Supports English and Chinese math problems through CoT and TIR
- Not recommended for non-math tasks
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.