Model	Pick	Confidence	Total · O/U 8.5	Result
AI consensus 8/8	MIL	60%	8.8 Over · 7/8	✗
GLM 5.2 56% on 515 graded	MIL	59%	9.0 Over ✗	✗
Claude Opus 4.8 58% on 547 graded	MIL	65%	8.9 Over ✗	✗
Grok 4.5 55% on 414 graded	MIL	61%	8.5 Over ✗	✗
DeepSeek V4 Pro 56% on 479 graded	MIL	63%	7.7 Under ✓	✗
Claude Sonnet 5 57% on 527 graded	MIL	59%	9.3 Over ✗	✗
GPT-5.6 Luna Pro 57% on 414 graded	MIL	61%	8.6 Over ✗	✗
Gemini 3.6 Flash 56% on 273 graded	MIL	59%	8.8 Over ✗	✗
Kimi K3 54% on 352 graded	MIL	56%	9.5 Over ✗	✗

Finals are revealed for everyone: the graded record is the product. Rose = the model broke from the consensus. O/U calls grade against the closing line (8.5); a push grades nothing.

Expert	Market	Pick	Price	Result
DRatings DRatings · Ratings model	Winner	MIL	-139	✗
Dimers Dimers · Ratings model	Winner	MIL	-135	✗
CBS Sports Staff CBS Sports · Staff picks	Winner	MIL	-144	✗
Dunkel Index Dunkel Index · Computer rating	Winner	MIL	—	✗
ESPN BPI ESPN · Matchup Predictor	Winner	MIL	—	✗
Justin Ziolkowski Pickswise	Winner	MIL	—	✗
Covers Consensus Covers · Community consensus	Winner	MIL	-141	✗

Captured from public sources and frozen at first pitch (named experts never edited after first capture; consensus pickers track the crowd until game time). A pick only grades when it existed before the game started.