Reasoning on BBH (Accuracy and ECE)
67.56Accuracy
gemma3-27b-slerp
Updated 22d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 67.56 | 0.209 | |
2025.10 | 67.52 | 0.232 | |
2025.10 | 67.23 | 0.161 | |
2025.10 | 67.21 | 0.302 | |
2025.10 | 67.12 | 0.133 | |
2025.10 | 67.07 | 0.189 | |
2025.10 | 66.69 | 0.104 | |
2025.10 | 65.86 | 0.075 | |
2025.10 | 65.28 | 0.037 | |
2025.10 | 65.18 | 0.038 | |
2025.10 | 64.03 | 0.015 | |
2025.10 | 63.79 | 0.017 | |
2025.10 | 63.27 | 0.325 | |
2025.10 | 63.2 | 0.228 | |
2025.10 | 62.91 | 0.229 | |
2025.10 | 62.85 | 0.17 | |
2025.10 | 62.66 | 0.172 | |
2025.10 | 62.63 | 0.202 | |
2025.10 | 62.59 | 0.203 | |
2025.10 | 62.51 | 0.172 | |
2025.10 | 62.49 | 0.259 | |
2025.10 | 62.47 | 0.203 | |
2025.10 | 62.45 | 0.26 | |
2025.10 | 62.02 | 0.135 | |
2025.10 | 61.88 | 0.236 | |
2025.10 | 61.74 | 0.146 | |
2025.10 | 61.66 | 0.147 | |
2025.10 | 61.66 | 0.049 | |
2025.10 | 61.34 | 0.291 | |
2025.10 | 61.08 | 0.112 | |
2025.10 | 60.81 | 0.116 | |
2025.10 | 60.39 | 0.118 | |
2025.10 | 60.06 | 0.083 | |
2025.10 | 59.76 | 0.085 | |
2025.10 | 59.16 | 0.089 | |
2025.10 | 57.82 | 0.059 | |
2025.10 | 57.79 | 0.059 | |
2025.10 | 57.75 | 0.064 | |
2025.10 | 55.89 | 0.034 | |
2025.10 | 55.89 | 0.035 | |
2025.10 | 55.84 | 0.032 | |
2025.10 | 54.31 | 0.022 |