GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
DORAEMONG
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
DORAEMONG
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Method | Train data | HotpotQA | PopQA | 2Wiki | Bamboogle | Musique | AVG |
|---|---|---|---|---|---|---|---|
| Search-R1 | ~90,000 | 37.88 / 49.56 | 40.65 / 46.78 | 34.87 / 42.50 | 33.60 / 43.55 | 12.99 / 21.23 | 32.00 / 40.72 |
| ReasonRAG | ~5,000 | 36.37 / 47.51 | 37.78 / 44.87 | 39.80 / 46.32 | 38.40 / 46.86 | 10.59 / 19.22 | 32.59 / 40.96 |
| StepSearch | ~19,000 | 38.72 / 50.67 | 39.24 / 44.97 | 40.38 / 47.12 | 33.60 / 44.16 | 13.82 / 23.06 | 33.15 / 42.00 |
| PRO-STEP (ours) ★ | 5,000 | 38.73 / 51.63 | 40.47 / 47.37 | 44.07 / 51.43 | 36.80 / 47.63 | 12.49 / 22.41 | 34.51 / 44.09 |
EM / F1 (Strict EM, token-F1). Bootstrap 95% CI: vs Search-R1 +2.51 EM [+1.01, +4.06], vs ReasonRAG +1.93 EM [+0.46, +3.36].
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B", torch_dtype="auto")tokenizer = AutoTokenizer.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B")# Use with FlashRAG SearchR1Pipeline or any agentic-RAG inference loop# System prompt: see paper Appendix A
bibtex
@article{prostep2026,title={PRO-STEP: Step-level Process Reward Optimization for Retrieval-Augmented Generation},author={...},year={2026}}