Math Reasoning on BeyondBench Easy
96.67AccuracyEFFGEN
Evaluation results
| Method | Links | |
|---|---|---|
| EFFGENBackbone=Qwen2.5-32B-Instruct2026.01 | 96.67 | |
| SmolagentsBackbone=Qwen2.5-32B-Instruct2026.01 | 94.63 | |
| AutogenBackbone=Qwen2.5-32B-Instruct2026.01 | 92.44 | |
| EFFGENBackbone=Qwen2.5-14B-Instruct2026.01 | 92.27 | |
| EFFGENBackbone=Qwen2.5-7B-Instruct2026.01 | 89.02 | |
| LangChainBackbone=Qwen2.5-32B-Instruct2026.01 | 88.05 | |
| SmolagentsBackbone=Qwen2.5-14B-Instruct2026.01 | 86.27 | |
| EFFGENBackbone=Qwen2.5-3B-Instruct2026.01 | 81.71 | |
| SmolagentsBackbone=Qwen2.5-7B-Instruct2026.01 | 80.24 | |
| AutogenBackbone=Qwen2.5-7B-Instruct2026.01 | 77.8 | |
| AutogenBackbone=Qwen2.5-14B-Instruct2026.01 | 77.07 | |
| LangChainBackbone=Qwen2.5-14B-Instruct2026.01 | 74.71 | |
| EFFGENBackbone=Qwen2.5-1.5B-Instruct2026.01 | 73.66 | |
| LangChainBackbone=Qwen2.5-7B-Instruct2026.01 | 72.2 | |
| Raw ModelBackbone=Qwen2.5-32B-Instruct2026.01 | 71.56 | |
| Raw ModelBackbone=Qwen2.5-14B-Instruct2026.01 | 64.63 | |
| SmolagentsBackbone=Qwen2.5-3B-Instruct2026.01 | 63.41 | |
| Raw ModelBackbone=Qwen2.5-7B-Instruct2026.01 | 59.68 | |
| AutogenBackbone=Qwen2.5-3B-Instruct2026.01 | 58.78 | |
| SmolagentsBackbone=Qwen2.5-1.5B-Instruct2026.01 | 56.39 | |
| AutogenBackbone=Qwen2.5-1.5B-Instruct2026.01 | 52.95 | |
| LangChainBackbone=Qwen2.5-3B-Instruct2026.01 | 52.68 | |
| LangChainBackbone=Qwen2.5-1.5B-Instruct2026.01 | 49.39 | |
| Raw ModelBackbone=Qwen2.5-3B-Instruct2026.01 | 42.05 | |
| Raw ModelBackbone=Qwen2.5-1.5B-Instruct2026.01 | 35.98 |