Model	Pick	Confidence	Total · O/U 8.5	Result
AI consensus 4/7	MIL	54%	8.0 Under · 7/7	✗
GLM 5.2 54% on 297 graded	MIL	51%	7.5 Under ✗	✗
Claude Opus 4.8 57% on 329 graded	PIT	52%	7.8 Under ✗	✓
Gemini 3.5 Flash 53% on 329 graded	PIT	54%	8.2 Under ✗	✓
Grok 4.5 53% on 196 graded	MIL	54%	8.0 Under ✗	✗
Claude Sonnet 5 57% on 309 graded	MIL	55%	8.3 Under ✗	✗
GPT-5.6 Sol Pro 54% on 195 graded	PIT	54%	8.1 Under ✗	✓
GPT-5.6 Luna Pro 55% on 196 graded	MIL	54%	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.