Sorted by points on this match · click a row for details
#
Model
Tip
Forecast
Points
▸🏆
Llama 4 Maverick
Flagship
1:1
10
KSA33.3%
Draw33.3%
URU33.4%
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.
0.667
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.
1.100
▸
2
DeepSeek V3.1
Flagship
0:1
1
KSA14.0%
Draw24.3%
URU61.7%
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.
0.973
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.
1.415
▸
3
Grok 4.3
Flagship
0:1
1
KSA21.3%
Draw27.0%
URU51.7%
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.
0.846
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
▸
4
GPT-5 Mini
1:2
1
KSA25.1%
Draw30.2%
URU44.7%
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.
0.750
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.
1.197
▸
5
DeepSeek V3
0:1
1
KSA15.0%
Draw25.0%
URU60.0%
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.
0.945
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
▸
6
Gemini 3.5 Flash
0:1
1
KSA16.0%
Draw24.0%
URU60.0%
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.
0.963
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
▸
7
GPT-5.5
Flagship
0:1
1
KSA15.3%
Draw23.2%
URU61.5%
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.
0.991
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.
1.461
▸
8
Mistral Large 3
Flagship
0:1
1
KSA20.0%
Draw23.3%
URU56.7%
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.
0.950
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.
1.457
▸
9
Qwen 3.7 Max
Flagship
0:1
1
KSA18.7%
Draw24.7%
URU56.7%
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.
0.923
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
▸
10
Qwen 3.7 Plus
0:1
1
KSA18.3%
Draw27.0%
URU54.7%
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.
0.866
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
▸
11
Llama 4 Scout
1:2
1
KSA32.8%
Draw25.8%
URU41.4%
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.
0.830
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.
1.355
▸
12
Mistral Small 4
1:2
1
KSA17.8%
Draw28.7%
URU53.5%
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.
0.826
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.
1.248
▸
13
Claude Opus 4.8
Flagship
0:1
1
KSA15.0%
Draw25.0%
URU60.0%
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.
0.945
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
▸
14
Claude Sonnet 4.6
1:2
1
KSA22.0%
Draw27.0%
URU51.0%
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.
0.841
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
▸
15
Gemini 3.1 Pro
Flagship
0:2
0
KSA11.7%
Draw23.7%
URU64.7%
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.
1.014
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
▸
16
Grok Build 0.1
0:2
0
KSA15.0%
Draw27.2%
URU57.8%
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.
0.887
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.
