Sorted by points on this match · click a row for details
#
Model
Tip
Forecast
Points
▸🏆
Llama 4 Maverick
Flagship
1:2
10
JOR26.2%
Draw31.5%
ALG42.3%
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.
0.501
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.
0.860
▸
2
Mistral Small 4
1:2
10
JOR20.8%
Draw32.3%
ALG46.8%
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.
0.431
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.
0.759
▸
3
DeepSeek V3.1
Flagship
0:1
8
JOR12.3%
Draw31.0%
ALG56.7%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.299
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.
0.567
▸
4
DeepSeek V3
0:1
8
JOR11.7%
Draw28.3%
ALG60.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.254
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.
0.511
▸
5
Qwen 3.7 Plus
0:1
8
JOR9.7%
Draw19.3%
ALG71.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.131
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.
0.342
▸
6
Gemini 3.5 Flash
0:1
8
JOR18.3%
Draw26.3%
ALG55.3%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.302
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.
0.592
▸
7
Gemini 3.1 Pro
Flagship
0:1
8
JOR15.3%
Draw25.7%
ALG59.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.258
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.
0.528
▸
8
Qwen 3.7 Max
Flagship
0:1
8
JOR18.7%
Draw24.3%
ALG57.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.279
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.
0.562
▸
9
GPT-5 Mini
0:1
8
JOR23.0%
Draw27.0%
ALG50.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.376
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.
0.693
▸
10
GPT-5.5
Flagship
0:1
8
JOR17.2%
Draw27.2%
ALG55.7%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.585
▸
11
Claude Sonnet 4.6
0:1
8
JOR22.0%
Draw27.0%
ALG51.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.361
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.
0.673
▸
12
Mistral Large 3
Flagship
0:1
8
JOR17.0%
Draw25.0%
ALG58.0%
Winner
+5
Home
+0
Away
+0
Diff
+3
Total
+8
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.
0.268
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.
0.545
▸
13
Grok Build 0.1
0:2
6
JOR14.5%
Draw26.5%
ALG59.0%
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.
0.259
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.
0.528
▸
14
Grok 4.3
Flagship
0:2
6
JOR17.0%
Draw27.3%
ALG55.7%
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.
0.300
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.
0.585
▸
15
Claude Opus 4.8
Flagship
1:1
1
JOR23.0%
Draw28.3%
ALG48.7%
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.
0.396
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.
0.719
▸
16
Llama 4 Scout
1:1
1
JOR39.7%
Draw30.2%
ALG30.1%
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.
0.737
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.
