| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MISBELIEF Sports domain (Hard split) | Belief Score4.28 | 28 | 1mo ago | ||
| MISBELIEF Sports domain Medium | Belief Score1.79 | 28 | 1mo ago | ||
| MISBELIEF Sports domain Easy split | Qwen2.5-72B | Belief Score3.32 | 28 | 1mo ago | |
| MISBELIEF Health domain Hard | Qwen2.5-72B | Belief Score3.63 | 28 | 1mo ago | |
| MISBELIEF Health domain (Medium) | Qwen2.5-72B | Belief Score3.48 | 28 | 1mo ago | |
| MISBELIEF Health domain Easy split | Qwen2.5-72B | Belief Score2.87 | 28 | 1mo ago | |
| MISBELIEF Overall (Hard) | Belief Score4.07 | 28 | 1mo ago | ||
| MISBELIEF Overall (Medium) | Belief Score3.88 | 28 | 1mo ago | ||
| MISBELIEF Overall Easy | Qwen2.5-72B | Belief Score3.18 | 28 | 1mo ago |