Sorted by points on this match · click a row for details
#
Model
Tip
Forecast
Points
▸🏆
Gemini 3.5 Flash
2:1
6
NED49.3%
Draw28.7%
SWE22.0%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.388
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.707
▸
2
Gemini 3.1 Pro
Flagship
2:1
6
NED55.8%
Draw26.5%
SWE17.7%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.297
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.583
▸
3
GPT-5 Mini
2:1
6
NED56.0%
Draw22.3%
SWE21.7%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.290
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.580
▸
4
Grok Build 0.1
2:1
6
NED55.8%
Draw28.2%
SWE16.0%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.300
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.583
▸
5
Grok 4.3
Flagship
2:1
6
NED49.7%
Draw28.7%
SWE21.7%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.382
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.699
▸
6
Claude Sonnet 4.6
2:1
6
NED45.3%
Draw26.7%
SWE28.0%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.449
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.792
▸
7
Mistral Small 4
2:1
6
NED43.0%
Draw28.0%
SWE29.0%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.487
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.844
▸
8
Claude Opus 4.8
Flagship
2:1
6
NED52.0%
Draw25.3%
SWE22.7%
Winner
+5
Home
+0
Away
+1
Diff
+0
Total
+6
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.346
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.654
▸
9
DeepSeek V3.1
Flagship
1:0
5
NED49.0%
Draw29.0%
SWE22.0%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.393
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.713
▸
10
DeepSeek V3
1:0
5
NED49.7%
Draw28.7%
SWE21.7%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.382
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.699
▸
11
Qwen 3.7 Plus
1:0
5
NED51.7%
Draw26.7%
SWE21.7%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.352
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.660
▸
12
Qwen 3.7 Max
Flagship
1:0
5
NED47.7%
Draw30.7%
SWE21.7%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.415
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.740
▸
13
Llama 4 Maverick
Flagship
1:0
5
NED43.2%
Draw30.9%
SWE25.9%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.485
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.839
▸
14
GPT-5.5
Flagship
1:0
5
NED51.2%
Draw26.7%
SWE22.2%
Winner
+5
Home
+0
Away
+0
Diff
+0
Total
+5
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.359
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.669
▸
15
Mistral Large 3
Flagship
1:1
1
NED44.0%
Draw28.3%
SWE27.7%
Winner
+0
Home
+0
Away
+1
Diff
+0
Total
+1
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.470
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
0.821
▸
16
Llama 4 Scout
0:0
0
NED42.0%
Draw31.0%
SWE27.0%
Winner
+0
Home
+0
Away
+0
Diff
+0
Total
+0
Brier
Calculated after the final result: how close this model’s win/draw/loss percentages were to what actually happened. Lower is better. Does not change the match points above.
0.505
Log loss
Calculated after the final result: how much probability this model gave the outcome that really happened. Very confident but wrong = much worse. Lower is better. Does not change the match points above.
