GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
TianHongZXY
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
TianHongZXY
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
CHIMERA is a compact synthetic reasoning dataset of 9,225 problems spanning 8 scientific disciplines and 1,179 fine-grained topics, each paired with a long Chain-of-Thought (CoT) reasoning trajectory. All problems are generated, validated and solved by LLMs without human annotation. Despite its modest size, post-training Qwen3-4B-Thinking-2507 on CHIMERA approaches or matches the reasoning performance of substantially larger models such as DeepSeek-R1 and Qwen3-235B.
| Model | GPQA-D | AIME 24 | AIME 25 | AIME 26 | HMMT Feb 25 | HMMT Nov 25 | HLE |
|---|---|---|---|---|---|---|---|
| Qwen3.5-4B | 76.2 | 86.5 | 80.4 | 85.4 | 74.0 | 76.8 | 12.9 |
| CHIMERA-Qwen3.5-4B-SFT | 79.7 | 88.0 | 83.1 | 86.3 | 72.8 | 74.5 | 12.7 |
All results use temperature = 0.6, top-p = 0.95, top-k = 20 and a maximum of 102,400 tokens. We sample 32 solutions per problem for AIME and HMMT, 10 for GPQA-Diamond, and 8 for Humanity's Last Exam.
bibtex
@article{zhu2026chimera, title={CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning}, author={Zhu, Xinyu and Feng, Yihao and Sun, Yanchao and Du, Xianzhi and Li, Pingzhi and Saarikivi, Olli and Zhu, Yun and Meng, Yu}, journal={arXiv preprint arXiv:2603.00889}, year={2026}}