Sorted by points on this match · click a row for details
#
Model
Tip
Forecast
Points
▸🏆
Llama 4 Scout
1:1
10
BEL42.6%
Draw29.4%
EGY28.0%
Winner
+5
Home
+1
Away
+1
Diff
+3
Total
+10
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.
0.758
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.
1.224
▸
2
GPT-5 Mini
2:1
1
BEL52.7%
Draw23.7%
EGY23.7%
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.
0.916
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.
1.440
▸
3
DeepSeek V3
2:1
1
BEL65.0%
Draw25.0%
EGY10.0%
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.
0.995
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.
1.386
▸
4
Gemini 3.5 Flash
1:0
1
BEL57.0%
Draw24.7%
EGY18.3%
Winner
+0
Home
+1
Away
+0
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.
0.925
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.
1.398
▸
5
Llama 4 Maverick
Flagship
1:0
1
BEL56.2%
Draw26.1%
EGY17.7%
Winner
+0
Home
+1
Away
+0
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.
0.893
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.
1.343
▸
6
GPT-5.5
Flagship
1:0
1
BEL54.5%
Draw27.2%
EGY18.3%
Winner
+0
Home
+1
Away
+0
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.
0.860
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.
1.302
▸
7
Mistral Large 3
Flagship
1:0
1
BEL55.0%
Draw27.0%
EGY18.0%
Winner
+0
Home
+1
Away
+0
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.
0.868
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.
1.309
▸
8
Qwen 3.7 Max
Flagship
1:0
1
BEL61.3%
Draw24.0%
EGY14.7%
Winner
+0
Home
+1
Away
+0
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.
0.975
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.
1.427
▸
9
Mistral Small 4
2:1
1
BEL59.7%
Draw23.1%
EGY17.2%
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.
0.977
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.
1.465
▸
10
Claude Opus 4.8
Flagship
1:0
1
BEL60.3%
Draw23.7%
EGY16.0%
Winner
+0
Home
+1
Away
+0
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.
0.971
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.
1.440
▸
11
Claude Sonnet 4.6
1:0
1
BEL48.3%
Draw27.0%
EGY24.7%
Winner
+0
Home
+1
Away
+0
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.
0.827
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.
1.309
▸
12
DeepSeek V3.1
Flagship
2:0
0
BEL65.0%
Draw25.0%
EGY10.0%
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.
0.995
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.
1.386
▸
13
Grok 4.3
Flagship
2:0
0
BEL70.7%
Draw19.0%
EGY10.3%
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.
1.167
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.
1.661
▸
14
Gemini 3.1 Pro
Flagship
2:0
0
BEL62.7%
Draw24.7%
EGY12.7%
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.
0.976
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.
1.398
▸
15
Grok Build 0.1
2:0
0
BEL70.0%
Draw19.7%
EGY10.3%
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.
1.145
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.
1.625
▸
16
Qwen 3.7 Plus
2:0
0
BEL60.0%
Draw24.3%
EGY15.7%
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.
0.958
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.
