You can deploy this model and start earning money today!

Kwai-Klear/
Klear-Reasoner-8B-SFT

Name: Klear-Reasoner-8B-SFT
Availability: InStock

safetensors

qwen3

Kwai-Klear/KlearReasoner-MathSub-30K

Kwai-Klear/KlearReasoner-CodeSub-15K

Views

No views yet

✨ Klear-Reasoner-8B-SFT

We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. We investigate two key issues with current clipping mechanisms in RL: Clipping suppresses critical exploration signals and ignores suboptimal trajectories. To address these challenges, we propose Gradient-Preserving clipping Policy Optimization (GPPO) that gently backpropagates gradients from clipped tokens.

Resource	Link
📝 Preprints	Paper
🤗 Daily Paper	Paper
🤗 Model Hub	Klear-Reasoner-8B
🤗 Dataset Hub	Math RL
🤗 Dataset Hub	Code RL
🐛 Issues & Discussions	GitHub Issues
📧 Contact	suzhenpeng13@163.com

📌 Overview

_{Benchmark accuracy of Klear-Reasoner-8B on AIME 2024/2025 (avg@64), LiveCodeBench V5 (2024/08/01-2025/02/01, avg@8), and v6 (2025/02/01-2025/05/01, avg@8).}

Klear-Reasoner is an 8-billion-parameter reasoning model that achieves SOTA performance on challenging math and coding benchmarks:

Benchmark	AIME 2024	AIME 2025	LiveCodeBench V5	LiveCodeBench V6
Score	90.5 %	83.2 %	66.0 %	58.1 %

The model combines:

Quality-centric long CoT SFT – distilled from DeepSeek-R1-0528.
Gradient-Preserving Clipping Policy Optimization (GPPO) – a novel RL method that keeps gradients from clipped tokens to boost exploration & convergence.

Evaluation

When we expand the inference budget to 64K and adopt the YaRN method with a scaling factor of 2.5. Evaluation is coming soon, stay tuned.

📊 Benchmark Results (Pass@1)

Model	AIME2024 avg@64	AIME2025 avg@64	HMMT2025 avg@64	LCB V5 avg@8	LCB V6 avg@8
AReal-boba-RL-7B	61.9	48.3	29.4	34.3	31.0†
MiMo-7B-RL	68.2	55.4	35.7	57.8	49.3
Skywork-OR1-7B	70.2	54.6	35.7	47.6	42.7
AceReason-Nemotron-1.1-7B	72.6	64.8	42.9	57.2	52.1
POLARIS-4B-Preview	81.2	79.4	58.7	58.5†	53.0†
Qwen3-8B	76.0	67.3	44.7†	57.5	48.4†
Deepseek-R1-0528-Distill-8B	86.0	76.3	61.5	61.0†	51.6†
OpenReasoning-Nemotron-7B	84.7	78.2	63.5	65.6†	56.3†
Klear-Reasoner-8B-SFT	75.6	70.1	57.6	58.5	49.6
Klear-Reasoner-8B	83.2	75.6	60.3	61.6	53.1
w/ 64K Inference Budget	90.5	83.2	70.8	66.0	58.1

We report the average pass@1 results (avg@n), with all other evaluation metrics following the DeepSeek-R1 assessment framework (temperature=0.6, top_p=0.95).

🧪 Training

Configure the experimental environment

bash

git clone https://github.com/suu990901/Klear_Reasoner
cd Klear_Reasoner
pip install -r requirements.txt

For the code, we use Firejail for the sandbox environment. Additionally, we implemented multi-process control based on Pebble, enabling automatic resource reclamation upon task timeout. For mathematics, we use math_verify for judging.

Using Ray for Multi-Node Training

For multi-node training, ensure all nodes are started and connected via Ray before executing the training script. Below is a brief setup guide for Ray across multiple machines:

Step 1: Start Ray on the Head Node (node0)

On the first node (typically called node0), run:

ray start --head --dashboard-host=0.0.0.0

Get the IP address of the master node.

MASTER_IP=$(hostname -I | awk '{print $1}')

Step 2: Connect Other Nodes (e.g., node1)

On each additional worker node (e.g., node1), run the following, replacing the IP with that of your head node:

ray start --address=\"$MASTER_IP:6379\"

RL Training

Run the following script on the master node to start the training task.

bash

bash recipe/dapo/perf_run_dapo_ours_math.sh # For Math RL
bash recipe/dapo/perf_run_dapo_ours_code.sh # For Code RL

In the startup script, you need to set the following variables:

bash

YOUR_MODEL_PATH="<your_model_path>"
CKPTS_SAVE_DIR="<ckpts_save_path>"
YOUR_TRAIN_FILE="<train_data_path>"
YOUR_TEST_FILE="<test_data_path>"

🤝 Citation

If you find this work helpful, please cite our paper:

bibtex

@misc{su2025cegppocontrollingentropygradientpreserving,
      title={CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning}, 
      author={Zhenpeng Su and Leiyu Pan and Minxuan Lv and Yuntao Li and Wenping Hu and Fuzheng Zhang and Kun Gai and Guorui Zhou},
      year={2025},
      eprint={2509.20712},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2509.20712}, 
}

bibtex

@article{DBLP:journals/corr/abs-2508-07629,
  author       = {Zhenpeng Su and
                  Leiyu Pan and
                  Xue Bai and
                  Dening Liu and
                  Guanting Dong and
                  Jiaming Huang and
                  Wenping Hu and
                  Fuzheng Zhang and
                  Kun Gai and
                  Guorui Zhou},
  title        = {Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving
                  Clipping Policy Optimization},
  journal      = {CoRR},
  volume       = {abs/2508.07629},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2508.07629},
  doi          = {10.48550/ARXIV.2508.07629},
  eprinttype    = {arXiv},
  eprint       = {2508.07629},
  timestamp    = {Sat, 13 Sep 2025 14:46:27 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2508-07629.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Kwai-Klear/Klear-Reasoner-8B-SFT

✨ Klear-Reasoner-8B-SFT

📌 Overview

Evaluation

📊 Benchmark Results (Pass@1)

🧪 Training

Configure the experimental environment

Using Ray for Multi-Node Training

Step 1: Start Ray on the Head Node (node0)

Step 2: Connect Other Nodes (e.g., node1)

RL Training

🤝 Citation

Kwai-Klear/
Klear-Reasoner-8B-SFT