Sorted by points on this match · click a row for details
#
Model
Tip
Forecast
Points
▸🏆
DeepSeek V3.1
Flagship
2:0
5
SWE64.0%
Draw25.0%
TUN11.0%
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.
0.204
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.
0.446
▸
2
Grok 4.3
Flagship
1:0
5
SWE53.7%
Draw27.3%
TUN19.0%
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.
0.325
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.
0.622
▸
3
GPT-5 Mini
1:0
5
SWE46.3%
Draw30.3%
TUN23.3%
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.
0.434
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.
0.770
▸
4
DeepSeek V3
1:0
5
SWE55.0%
Draw30.0%
TUN15.0%
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.
0.315
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.
0.598
▸
5
Gemini 3.5 Flash
1:0
5
SWE52.0%
Draw27.7%
TUN20.3%
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.
0.348
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
▸
6
GPT-5.5
Flagship
1:0
5
SWE45.8%
Draw30.2%
TUN24.0%
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.
0.443
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.
0.781
▸
7
Gemini 3.1 Pro
Flagship
1:0
5
SWE55.3%
Draw29.7%
TUN15.0%
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.
0.311
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
▸
8
Grok Build 0.1
1:0
5
SWE53.7%
Draw30.0%
TUN16.3%
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.
0.331
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.
0.622
▸
9
Qwen 3.7 Max
Flagship
1:0
5
SWE41.7%
Draw30.0%
TUN28.3%
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.
0.510
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.
0.875
▸
10
Qwen 3.7 Plus
1:0
5
SWE46.7%
Draw29.3%
TUN24.0%
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.
0.428
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.
0.761
▸
11
Llama 4 Scout
1:0
5
SWE42.6%
Draw27.7%
TUN29.7%
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.
0.494
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.
0.853
▸
12
Claude Sonnet 4.6
1:0
5
SWE48.7%
Draw27.7%
TUN23.7%
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.
0.396
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
▸
13
Llama 4 Maverick
Flagship
1:1
1
SWE39.4%
Draw32.4%
TUN28.2%
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.
0.552
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.
0.931
▸
14
Mistral Large 3
Flagship
1:1
1
SWE45.0%
Draw29.3%
TUN25.7%
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.
0.454
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.
0.799
▸
15
Mistral Small 4
1:1
1
SWE44.3%
Draw28.7%
TUN27.0%
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.
0.466
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.
0.814
▸
16
Claude Opus 4.8
Flagship
1:1
1
SWE40.7%
Draw29.7%
TUN29.7%
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.
0.528
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.
