KicktippAi experiment analysis

match-predictions/bundesliga-2025-26/pes-squad/slices/all-matchdays/random-16-seed-578661

Task: task-5 Primary metric: total_kicktipp_points Runs: 2 Pairings: 16

Summary

Datasetmatch-predictions/bundesliga-2025-26/pes-squad/slices/all-matchdays/random-16-seed-578661

Task typetask-5

Primary metrictotal_kicktipp_points

Alpha0.0500

Rank	Run	Model	Primary metric
1	task-5__pes-squad__o3__prompt-v1__-12h__2026-04-03t23-43-14z	o3	23.0000
2	task-5__pes-squad__gpt-5-nano__prompt-v1__-12h__2026-04-03t23-43-14z	gpt-5-nano	18.0000

not significant

Better runtask-5__pes-squad__o3__prompt-v1__-12h__2026-04-03t23-43-14z

Other runtask-5__pes-squad__gpt-5-nano__prompt-v1__-12h__2026-04-03t23-43-14z

total_kicktipp_points delta5.0000

Wilcoxon p-value0.2763

Mean difference0.3125

Median difference0.0000

Per-item W/T/L2/13/1

Statistic	Point estimate	Low	High
Mean difference	0.3125	-0.2500	0.7500
Median difference	0.0000	0.0000	0.0000

Per-item win/tie/loss counts compare paired Kicktipp points for the listed run ordering on each prepared dataset item.