| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| GSM8K | GHG-TDA | Accuracy97.1 | 1,424 | 24d ago | |
| GSM8K (test) | Accuracy99 | 954 | 1mo ago | ||
| MATH500 (test) | Accuracy60.9 | 922 | 17d ago | ||
| MATH | CoD | Accuracy95.63 | 882 | 3mo ago | |
| GSM8K (test) | ReProbe | Accuracy98.8 | 816 | 2mo ago | |
| MATH 500 | Qwen3-Base SAT | Accuracy (Acc)99.1 | 600 | 1mo ago | |
| MATH 500 | Qwen3-Base (DICE-PC) | Accuracy99.1 | 589 | 29d ago | |
| MathVista | Qwen-VL-7B-Chat | Score229.2 | 566 | 1mo ago | |
| MATH | Self-Reminder | Accuracy94.2 | 535 | 4mo ago | |
| AIME 2024 | DC-Tail | Accuracy93.3 | 525 | 1mo ago | |
| GSM8K | MARS | Accuracy98 | 499 | 4mo ago | |
| MATH 500 | PADD | Top-1 Accuracy96.4 | 452 | 1mo ago | |
| MATH 500 | SwiR | Accuracy98.4 | 442 | 4mo ago | |
| MATH (test) | IIPC | Overall Accuracy94.13 | 433 | 4mo ago | |
| SVAMP | GPT-4o + QuaSAR | Accuracy97 | 403 | 3mo ago | |
| AIME 2024 | ThoughtFold | Accuracy79.3 | 394 | 1mo ago | |
| GSM8k | Phi-4 pass@N (Upper Bound) | Accuracy100 | 388 | 2mo ago | |
| MathVista | Accuracy89.2 | 382 | 2mo ago | ||
| AIME 2025 | TRICE-30B | Accuracy99.2 | 378 | 1mo ago | |
| AMC | Qwen3-30B A3B-Instruct-2507 | Accuracy (%)95.18 | 375 | 1mo ago | |
| AIME 2024 | GPT-5-Mini-R | Accuracy94 | 370 | 4mo ago | |
| AIME 24 | DDC | Accuracy93.3 | 358 | 1mo ago | |
| GSM8K | Accuracy (GSM8K)97.8 | 358 | 4mo ago | ||
| MathQA | Accuracy98.84 | 354 | 2mo ago | ||
| AIME 2025 | PC-cubic | Accuracy96.7 | 353 | 1mo ago |