Model	Pick	Confidence	Total · O/U 8.5	Result
AI consensus 11/11	BOS	64%	8.3 Under · 9/11	✓
GLM 5.2 56% on 432 graded	BOS	64%	8.4 Under ✗	✓
Claude Opus 4.8 59% on 464 graded	BOS	66%	8.1 Under ✗	✓
Gemini 3.5 Flash 56% on 464 graded	BOS	64%	8.5 Over ✓	✓
Grok 4.5 55% on 331 graded	BOS	63%	8.4 Under ✗	✓
DeepSeek V4 Pro 57% on 406 graded	BOS	66%	8.4 Under ✗	✓
Claude Sonnet 5 57% on 444 graded	BOS	63%	8.4 Under ✗	✓
GPT-5.6 Luna Pro 57% on 331 graded	BOS	63%	8.1 Under ✗	✓
Gemini 3.5 Flash Lite 56% on 190 graded	BOS	58%	8.4 Under ✗	✓
Gemini 3.6 Flash 58% on 190 graded	BOS	65%	8.5 Over ✓	✓
Claude Opus 5 57% on 190 graded	BOS	65%	7.8 Under ✗	✓
Kimi K3 54% on 270 graded	BOS	64%	7.8 Under ✗	✓

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
Trevor Knapp Covers · Publishing Editor	Winner	BOS	-167	✓
CBS Sports Staff CBS Sports · Staff picks	Winner	BOS	-181	✓
Dimers Dimers · Ratings model	Winner	BOS	-175	✓
DRatings DRatings · Ratings model	Winner	BOS	-177	✓
Covers Consensus Covers · Community consensus	Winner	BOS	-192	✓

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.