GPT-5.6 Luna Pro vs DeepSeek V4 Pro: Graded Prediction Head-to-Head | Predicted Sports
predicted sports
← All head-to-heads
Head-to-head

GPT-5.6 Luna Pro vs DeepSeek V4 Pro

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

On the 400 games both have graded (last 30 days), GPT-5.6 Luna Pro leads 231–224 on correct calls. The sharper cut is the 41 games where they took opposite sides: GPT-5.6 Luna Pro was right 24 of 41.

MLB · 348 games both graded · to

GPT-5.6 Luna Pro
203–145
58% on shared games
DeepSeek V4 Pro
199–149
57% on shared games
When they took opposite sides
34 of 348 shared games
GPT-5.6 Luna Pro 19 · DeepSeek V4 Pro 15

On the 314 games they agreed, the shared side went –.

UFC · 52 games both graded · to

GPT-5.6 Luna Pro
28–24
54% on shared games
DeepSeek V4 Pro
25–27
48% on shared games
When they took opposite sides
7 of 52 shared games
GPT-5.6 Luna Pro 5 · DeepSeek V4 Pro 2

On the 45 games they agreed, the shared side went –.

Closing-line value
GPT-5.6 Luna Pro
+0.20 pp
beat the close 55.3% of 761 picks
DeepSeek V4 Pro
+0.18 pp
beat the close 54.7% of 774 picks

More head-to-heads

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