Model	Pick	Confidence	Total · O/U 8.5	Result
AI consensus 12/12	SF	64%	8.0 Under · 11/12	✓
GLM 5.2 55% on 286 graded	SF	63%	8.3 Under ✗	✓
Claude Opus 4.8 58% on 318 graded	SF	70%	8.2 Under ✗	✓
Gemini 3.5 Flash 54% on 318 graded	SF	66%	7.9 Under ✗	✓
Grok 4.5 53% on 185 graded	SF	64%	7.8 Under ✗	✓
DeepSeek V4 Pro 55% on 270 graded	SF	64%	8.2 Under ✗	✓
Claude Sonnet 5 57% on 298 graded	SF	68%	8.5 Over ✓	✓
GPT-5.6 Sol Pro 55% on 184 graded	SF	64%	8.3 Under ✗	✓
GPT-5.6 Luna Pro 55% on 185 graded	SF	63%	7.6 Under ✗	✓
Gemini 3.5 Flash Lite 55% on 44 graded	SF	62%	8.0 Under ✗	✓
Gemini 3.6 Flash 57% on 44 graded	SF	63%	8.0 Under ✗	✓
Claude Opus 5 55% on 44 graded	SF	65%	7.7 Under ✗	✓
Kimi K3 50% on 133 graded	SF	60%	7.6 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
CBS Sports Staff CBS Sports · Staff picks	Winner	SF	-173	✓
Dimers Dimers · Ratings model	Winner	SF	-156	✓
DRatings DRatings · Ratings model	Winner	SF	-156	✓
ESPN BPI ESPN · Matchup Predictor	Winner	SF	—	✓
Covers Consensus Covers · Community consensus	Winner	SF	-161	✓

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.