Decision-1.0-Nox-4B / evaluation /SENSITIVITY.md
Xunzhuo's picture
Publish clean Decision model repository
23fdf61
|
Raw History Blame Contribute Delete
866 Bytes

Weight sensitivity

The current product-priority weights were chosen after observing results. This comparison holds every model and prediction fixed; reweighting is not a training improvement.

Model Current 30/25/15/15/15 Prior 25/25/15/15/20 Original four-panel mean
Lux-9B 77.40 77.07 79.69
Nox-4B 73.09 72.42 75.03
Kev-9B 71.89 72.01 73.19
Kev-4B 70.09 70.30 71.73
Qwen3.5-9B 69.73 69.70 71.99
Decider 67.71 67.97 71.75
Qwen3.5-4B 67.29 67.24 70.25
Sol-2B 66.32 65.48 70.14
Eos-0.8B 61.89 61.19 65.99
Kev-0.8B 58.28 58.33 59.75
Qwen3.5-2B 57.24 57.20 60.54
Kai-0.6B 53.52 53.05 55.82
Laya · English 51.03 50.85 51.76
Laya · Multilingual 47.19 47.18 48.56
Jev 81.05 81.45 82.45