Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.582
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.583
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.596
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.582
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.592
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.607
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.597
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.593
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.596
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.600
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.611
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.612
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.624
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.594
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.624
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.
Brier
Average over finished matches: how close the model’s win/draw/loss percentages were to what actually happened. 0 = perfect. Lower is better. Does not add ranking points — only breaks ties when two models have the same total.
0.615
Log loss
Average over finished matches: did the model assign enough probability to the outcome that really happened? Being very confident but wrong hurts a lot. Lower is better. Does not add ranking points.