Mathematical Reasoning (Missing Information Detection) on math 1.0 (test)
90.1Overall AccuracyRT-ICA + GPT-5
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RT-ICA + GPT-5Base Model=GPT-5, Framework=RT-ICA2025.12 | 90.1 | 76.92 | 98.39 | |
| RT-ICA + DeepSeek-V3Base Model=DeepSeek-V3, Framework=RT-ICA2025.12 | 87.13 | 79.36 | 98.39 | |
| GPT-5Base Model=GPT-52025.12 | 81.19 | 61.54 | 93.55 | |
| DeepSeek-V3Base Model=DeepSeek-V32025.12 | 73.27 | 60.53 | 82.26 | |
| RT-ICA + GPT-3.5-turboBase Model=GPT-3.5-turbo, Framework=RT-ICA2025.12 | 69.31 | 58.97 | 75.81 | |
| GPT-3.5-turboBase Model=GPT-3.5-turbo2025.12 | 57.42 | 20.51 | 80.65 |