| --- |
| license: apache-2.0 |
| library_name: transformers |
| --- |
| # ReasoningModel |
|
|
| <!-- markdownlint-disable first-line-h1 --> |
| <!-- markdownlint-disable html --> |
| <!-- markdownlint-disable no-duplicate-header --> |
|
|
| <div align="center"> |
| <img src="figures/fig1.png" width="60%" alt="ReasoningModel" /> |
| </div> |
| <hr> |
|
|
| <div align="center" style="line-height: 1;"> |
| <a href="LICENSE" style="margin: 2px;"> |
| <img alt="License" src="figures/fig2.png" style="display: inline-block; vertical-align: middle;"/> |
| </a> |
| </div> |
| |
| ## 1. Introduction |
|
|
| ReasoningModel is optimized for complex reasoning tasks. This checkpoint is selected based on the combined performance of math reasoning and logical reasoning benchmarks. |
|
|
| <p align="center"> |
| <img width="80%" src="figures/fig3.png"> |
| </p> |
|
|
| Compared to general-purpose models, ReasoningModel demonstrates significantly improved performance on tasks requiring multi-step reasoning, mathematical computation, and logical inference. |
|
|
| ## 2. Evaluation Results |
|
|
| ### Comprehensive Benchmark Results |
|
|
| <div align="center"> |
|
|
| | | Benchmark | ReasonBase | ReasonPro | ReasoningModel | |
| |---|---|---|---|---| |
| | **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.550 | |
| | | Logical Reasoning | 0.789 | 0.801 | 0.819 | |
| | | Common Sense | 0.716 | 0.702 | 0.736 | |
| | **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.700 | |
| | | Question Answering | 0.582 | 0.599 | 0.607 | |
| | | Text Classification | 0.803 | 0.811 | 0.828 | |
| | | Sentiment Analysis | 0.777 | 0.781 | 0.792 | |
| | **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.650 | |
| | | Creative Writing | 0.588 | 0.579 | 0.610 | |
| | | Dialogue Generation | 0.621 | 0.635 | 0.644 | |
| | | Summarization | 0.745 | 0.755 | 0.767 | |
| | **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.804 | |
| | | Knowledge Retrieval | 0.651 | 0.668 | 0.676 | |
| | | Instruction Following | 0.733 | 0.749 | 0.758 | |
| | | Safety Evaluation | 0.718 | 0.701 | 0.739 | |
|
|
| </div> |
|
|
| ### Reasoning Performance Highlight |
|
|
| ReasoningModel achieves strong performance on both math reasoning and logical reasoning benchmarks, making it the best choice for reasoning-intensive applications. |
|
|
| ## 3. License |
| [Apache-2.0 License](LICENSE) |
|
|
| ## 4. Contact |
| Open an issue on GitHub. |
|
|
