GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CMU-AIRe
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CMU-AIRe
Model Tree
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Input Modalities
Output Modalities
Supported Functionality
pass@1 (mean of 64 samples/problem) at a 16K token budget, averaged over AIME 2024 / AIME 2025 / AMC 2023 / MinervaMATH / MATH500 (single grader used for training and eval):
| model | AIME24 | AIME25 | AMC23 | Minerva | MATH500 | Avg | gain over base |
|---|---|---|---|---|---|---|---|
| base (R1-Distill-Qwen-1.5B) | 27.34 | 22.86 | 67.89 | 24.94 | 81.71 | 44.95 | — |
| GRPO (outcome-reward) | 28.12 | 22.97 | 67.77 | 26.45 | 81.85 | 45.43 | +0.48 |
| MRT-offline (this model) | 28.75 | 23.59 | 70.86 | 24.96 | 82.61 | 46.16 | +1.20 |
MRT's gain over base (+1.20) is 2.5× the GRPO gain (+0.48) — within the paper's
reported 2–3× range. (Paper Table 1 reports +1.1 / +2.2 for GRPO / MRT; our reproduction
reaches a smaller absolute magnitude — see REPRODUCTION.md for the training-length and
grader notes.)
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B; data: 4,000 NuminaMath problems.train/rl/REPRODUCTION.md.bibtex
@misc{qu2025optimizingtesttimecomputemeta, title={Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning}, author={Yuxiao Qu and Matthew Y. R. Yang and Amrith Setlur and Lewis Tunstall and Edward Emanuel Beeching and Ruslan Salakhutdinov and Aviral Kumar}, year={2025}, eprint={2503.07572}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2503.07572},}@misc{qu2025optimizingtesttimecomputemeta, title={Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning}, author={Yuxiao Qu and Matthew Y. R. Yang and Amrith Setlur and Lewis Tunstall and Edward Emanuel Beeching and Ruslan Salakhutdinov and Aviral Kumar}, year={2025}, eprint={2503.07572}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2503.07572},}