Eurus-2-7B-PRIME
Tsinghua UniversityUniversity of Illinois Urbana-Champaign (UIUC)Shanghai AI LabPeking UniversityShanghai Jiao Tong UniversityCUHK Shenzhen Research InstituteMathematical reasoningCode generationOpen weights
The Eurus-2-7B-PRIME model is an open-weights mathematical reasoning model from Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute with 7000000000.0 parameters.
About Eurus-2-7B-PRIME
Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoning. While dense rewards also o
LLM pricing & performance
Full LLM page →Eurus-2-7B-PRIME is available via API — live cost, context, and benchmark data:
Input / 1M
—
Output / 1M
—
Context
—
Tokens/sec
—
GPQA Diamond: 33.9
Details
- Provider
- Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute
- Task
- Mathematical reasoning,Code generation
- Parameters
- 7000000000.0
- Released
- 2025-02-03
- Open weights
- Yes