GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
NP235
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
NP235
Model Tree
Input Modalities
Output Modalities
Supported Functionality
This Hugging Face repository hosts the model weights. The training and evaluation code is maintained in the GitHub repository:
Clone the code repository:
bash
git clone https://github.com/Simplified-Reasoning/SU-01.gitcd SU-01The project uses the slimerl/slime:nightly-dev-20260202c Docker image.
bash
docker pull slimerl/slime:nightly-dev-20260202c docker run --gpus all --ipc=host --network=host -it \ -v "$PWD":/workspace/SU-01 \ -w /workspace/SU-01/su01-train-slime \ slimerl/slime:nightly-dev-20260202c \ /bin/bashInside the container, install the local training package:
bash
pip install -e . --no-deps --no-index --disable-pip-version-check --no-build-isolationAdjust cluster mounts, model paths, data paths, Ray environment variables, and reward-server URLs according to your infrastructure.
The released training code contains the three major training stages used by SU-01:
text
su01-train-slime/scripts├── sft.sh # Stage 1: reverse-perplexity curriculum SFT├── coarse_rl.sh # Stage 2: coarse RL with verifiable rewards└── refined_rl.sh # Stage 3: refined RL with proof rewards, self-refinement, and experience replayGitHub links:
SU-01 uses a model-internal verification-and-refinement loop:
This expands the model's own natural-language proof-search computation rather than calling an external theorem prover, symbolic solver, or code executor. In the reported USAMO 2026 TTS traces, initial solution generations have a median length of approximately 106K tokens, while refinement stages have a median length of approximately 83K tokens.
The released TTS implementation is in su01-eval/decode, including direct decoding, TTS decoding, batch decoding, and SGLang server helpers. See su01-eval/decode/README.md for launch commands, input layout, decoding options, and smoke tests.
Rendered for readability, the default prompt is:
text
Please solve the following mathematical olympiad problem. Show your complete reasoning and proof.1. Please use LaTeX format to represent the variables and formulas used in the solution process and results.2. If the problem asks you to find specific values, please put the final answer(s) in \boxed{}.3. If the problem requires a proof, present a clear and rigorous argument.Evaluation code is released under su01-eval. Use su01-eval/decode to generate direct or TTS predictions, and use su01-eval/verifiable_bench to score answer-verifiable benchmarks and FrontierScience Olympiad predictions.
See su01-eval/decode/README.md and su01-eval/verifiable_bench/README.md for commands, input formats, output formats, and configuration options.
AnswerBench, AMO-Bench, AIME 25/26, and FrontierScience-Olympiad are averaged over 4, 8, 8, and 4 runs, respectively. Avg. is the mean of AnswerBench, AMO-Bench, AIME 2025, AIME 2026, and FrontierScience-Olympiad.
| Model | AnswerBench | AMO-Bench | AIME 25/26 | FS-O Physics | FS-O Chemistry | FS-O Biology | FS-O Overall | Avg. |
|---|---|---|---|---|---|---|---|---|
| P1-30B-A3B | 69.3% | 41.3% | 90.4% / 89.6% | 57.5% | 57.5% | 27.5% | 54.5% | 69.0% |
| GLM-4.7-Flash | 73.8% | 53.8% | 91.3% / 88.3% | 54.5% | 60.0% | 17.5% | 53.0% | 72.0% |
| Nemotron-Cascade-2 | 80.5% | 40.8% | 94.2% / 90.0% | 56.0% | 56.3% | 30.0% | 53.5% | 71.8% |
| Qwen3.6-35B-A3B | 78.0% | 58.8% | 92.5% / 92.9% | 65.5% | 74.4% | 25.0% | 65.0% | 77.4% |
| Gemma-4-31B | 74.0% | 39.3% | 88.8% / 91.3% | 69.0% | 61.9% | 27.5% | 61.0% | 70.9% |
| SU-01 | 77.5% | 59.8% | 94.6% / 93.3% | 62.5% | 69.4% | 25.0% | 61.5% | 77.3% |
FrontierScience-Research refers to the research subset of FrontierScience. For SU-01, x/y reports scores without and with TTS on IMO-ProofBench.
| Model | ProofBench Basic | ProofBench Advanced | ProofBench Overall | FS-R Physics | FS-R Chemistry | FS-R Biology | FS-R Overall |
|---|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Thinking | 95.2% | 50.0% | 72.6% | 0.0% | 30.0% | 10.0% | 13.3% |
| GPT-5.5-High | 96.7% | 64.8% | 80.7% | 25.0% | 40.0% | 45.0% | 36.7% |
| DeepSeek-V3.2-Speciale | 77.6% | 34.3% | 56.0% | 10.0% | 20.0% | 15.0% | 15.0% |
| P1-30B-A3B | 33.8% | 6.2% | 20.0% | 0.0% | 10.0% | 0.0% | 3.3% |
| GLM-4.7-Flash | 51.0% | 16.7% | 33.8% | 0.0% | 0.0% | 0.0% | 0.0% |
| Nemotron-Cascade-2 | 77.1% | 28.6% | 52.9% | 5.0% | 5.0% | 20.0% | 10.0% |
| Qwen3.6-35B-A3B | 39.1% | 7.1% | 23.1% | 0.0% | 5.0% | 10.0% | 5.0% |
| Gemma-4-31B | 46.7% | 16.2% | 31.4% | 0.0% | 10.0% | 5.0% | 5.0% |
| SU-01 | 77.1% / 91.0% | 38.1% / 49.5% | 57.6% / 70.2% | 10.0% | 10.0% | 15.0% | 11.7% |
For IPhO, x/y reports scores without and with TTS. Gold lines for IPhO 2024/2025 are 20.8/19.7 points. Medal lines for IMO 2025 are 35/28/19 points, and medal lines for USAMO 2026 are 25/18/11 points.
| Model | IPhO 2024 | IPhO 2025 |
|---|---|---|
| P1-30B-A3B | 23.1 | 17.7 |
| GLM-4.7-Flash | 22.2 | 19.5 |
| Nemotron-Cascade-2 | 21.2 | 16.7 |
| Qwen3.6-35B-A3B | 24.3 | 19.9 |
| Gemma-4-31B | 24.4 | 20.3 |
| SU-01 | 23.5 / 25.3 | 20.3 / 21.7 |
| Model | P1 | P2 | P3 | P4 | P5 | P6 | Total |
|---|---|---|---|---|---|---|---|
| SU-01 | 1 | 7 | 1 | 6 | 6 | 0 | 21 |
| SU-01 w/ TTS | 7* | 7* | 7* | 7* | 7* | 0* | 35* |
| Model | P1 | P2 | P3 | P4 | P5 | P6 | Total |
|---|---|---|---|---|---|---|---|
| SU-01 | 7 | 0 | 0 | 7 | 0 | 1 | 15 |
| SU-01 w/ TTS | 7* | 0* | 7* | 7* | 7* | 7* | 35* |
* denotes TTS results graded by human experts.
This work was supported by the Shanghai Artificial Intelligence Laboratory.
We thank the authors and maintainers of prior open research and infrastructure that made this work possible. In particular, we are grateful to DeepSeek for open-sourcing strong reasoning policies and generative reward models, which provided an important reference point for our work. IMO-Bench, AMO-Bench, and FrontierScience helped guide the overall system optimization by offering challenging mathematical and scientific reasoning benchmarks and evaluation protocols.
We also thank prior data efforts that supported our SFT and RL data curation, including DeepMath, NaturalReasoning, Eurus, OpenCodeReasoning, P1, and OPC, as well as the many public problem sources and communities that cannot all be listed here. We further acknowledge the broader open-source infrastructure ecosystem, including slime for training and SGLang for efficient inference and serving.
If you find SU-01 useful, please cite the project:
bibtex
@misc{su012026, title={Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling}, author={Yafu Li and Runzhe Zhan and Haoran Zhang and Shunkai Zhang and Yizhuo Li and Zhilin Wang and Jiacheng Chen and Futing Wang and Xuyang Hu and Yuchen Fan and Bangjie Xu and Yucheng Su and Xinmiao Han and Chenxi Li and Haodi Lei and Yufeng Zhao and Zejin Lin and Qianjia Cheng and Tong Zhu and Xiaoye Qu and Ganqu Cui and Peng Ye and Yun Luo and Zhouchen Lin and Yu Qiao and Bowen Zhou and Ning Ding and Yu Cheng}, year={2026}, url={http://arxiv.org/abs/2605.13301}}git clone https://github.com/Simplified-Reasoning/SU-01.gitcd SU-01docker pull slimerl/slime:nightly-dev-20260202c docker run --gpus all --ipc=host --network=host -it \ -v "$PWD":/workspace/SU-01 \ -w /workspace/SU-01/su01-train-slime \ slimerl/slime:nightly-dev-20260202c \ /bin/bashpip install -e . --no-deps --no-index --disable-pip-version-check --no-build-isolationsu01-train-slime/scripts├── sft.sh # Stage 1: reverse-perplexity curriculum SFT├── coarse_rl.sh # Stage 2: coarse RL with verifiable rewards└── refined_rl.sh # Stage 3: refined RL with proof rewards, self-refinement, and experience replayPlease solve the following mathematical olympiad problem. Show your complete reasoning and proof.1. Please use LaTeX format to represent the variables and formulas used in the solution process and results.2. If the problem asks you to find specific values, please put the final answer(s) in \boxed{}.3. If the problem requires a proof, present a clear and rigorous argument.@misc{su012026, title={Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling}, author={Yafu Li and Runzhe Zhan and Haoran Zhang and Shunkai Zhang and Yizhuo Li and Zhilin Wang and Jiacheng Chen and Futing Wang and Xuyang Hu and Yuchen Fan and Bangjie Xu and Yucheng Su and Xinmiao Han and Chenxi Li and Haodi Lei and Yufeng Zhao and Zejin Lin and Qianjia Cheng and Tong Zhu and Xiaoye Qu and Ganqu Cui and Peng Ye and Yun Luo and Zhouchen Lin and Yu Qiao and Bowen Zhou and Ning Ding and Yu Cheng}, year={2026}, url={http://arxiv.org/abs/2605.13301}}