Long-Context Mathematical Reasoning on GSM-Infinite
87.06AccuracyGemini-3.0-pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3.0-pro2026.03 | 87.06 | |
| Deepseek-v3.12026.03 | 47.4 | |
| Qwen3-32B + TableLong2026.03 | 23.4 | |
| Deepseek-R1-Distill-Qwen-32B + TableLong2026.03 | 14.8 | |
| Qwen2.5-32B-Instruct + TableLong2026.03 | 13 | |
| Qwen3-32B2026.03 | 12.22 | |
| Qwen2.5-32B-Instruct2026.03 | 9.6 | |
| Deepseek-R1-Distill-Qwen-14B + TableLong2026.03 | 9.6 | |
| Qwen-Long-L12026.03 | 9 | |
| Deepseek-R1-Distill-Qwen-14B2026.03 | 9 | |
| Deepseek-R1-Distill-Qwen-32B2026.03 | 6.6 |