GPT-5.6 Luna Pro vs Gemini 3.5 Flash: Graded Prediction Head-to-Head | Predicted Sports
predicted sports
Pro
← All head-to-heads
Head-to-head

GPT-5.6 Luna Pro vs Gemini 3.5 Flash

AI model vs AI model · same games, same finals, graded in public

On the 440 games both have graded (all time), they are dead even at 264 correct calls each. The sharper cut is the 44 games where they took opposite sides: they split them exactly, 22 apiece.

MLB · 376 games both graded · Jul 10 to Aug 9, 2026

GPT-5.6 Luna Pro
215–161
57% on shared games
Gemini 3.5 Flash
210–166
56% on shared games
When they took opposite sides
37 of 376 shared games
GPT-5.6 Luna Pro 21 · Gemini 3.5 Flash 16

On the 339 games they agreed, the shared side went 194–145.

UFC · 64 games both graded · Jul 11 to Aug 8, 2026

GPT-5.6 Luna Pro
49–15
77% on shared games
Gemini 3.5 Flash
54–10
84% on shared games
When they took opposite sides
7 of 64 shared games
GPT-5.6 Luna Pro 1 · Gemini 3.5 Flash 6

On the 57 games they agreed, the shared side went 48–9.

Closing-line value
GPT-5.6 Luna Pro
+0.30 pp
beat the close 56.3% of 416 picks
Gemini 3.5 Flash
+0.19 pp
beat the close 52.9% of 476 picks

More head-to-heads

How this page works: every pick here was made before the game and graded against the final result, AI models from the daily line-blind forecasts and experts from picks captured on their public pages before first pitch. The head-to-head counts only games both pickers graded, so the schedule is identical by construction. Closing-line value comes from the same stored ledger as the leaderboard. Updated nightly.