Who is better at picking games, Dunkel Index or Gemini 3.5 Flash Lite?

On the 25 games both have graded, Gemini 3.5 Flash Lite leads with 18 wins to 10. Every pick is made before the game and graded in public against the final result.

How often do Dunkel Index and Gemini 3.5 Flash Lite disagree?

They took opposite sides on 14 of the 25 shared games, and Gemini 3.5 Flash Lite was right 11 of those 14 times.

← All head-to-heads

Head-to-head

Dunkel Index vs Gemini 3.5 Flash Lite

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

All time Last 30 days Last 90 days

On the 25 games both have graded (all time), Gemini 3.5 Flash Lite leads 18–10 on correct calls. The sharper cut is the 14 games where they took opposite sides: Gemini 3.5 Flash Lite was right 11 of 14. A small shared sample; treat this as a story in progress, not proof.

MLB · 25 games both graded · Jul 24 to Jul 26, 2026

Dunkel Index

10–15

40% on shared games

Gemini 3.5 Flash Lite

18–7

72% on shared games

When they took opposite sides

14 of 25 shared games

Dunkel Index 3 · Gemini 3.5 Flash Lite 11

On the 11 games they agreed, the shared side went 7–4.

Closing-line value

Dunkel Index

-0.06 pp

beat the close 47.2% of 53 picks

Gemini 3.5 Flash Lite

-0.13 pp

beat the close 47.7% of 44 picks

More head-to-heads

Dunkel Index vs GLM 5.2 Dunkel Index vs Claude Opus 4.8 Dunkel Index vs Gemini 3.5 Flash Dunkel Index vs Grok 4.5 Dunkel Index vs DeepSeek V4 Pro Dunkel Index vs Claude Sonnet 5 Dunkel Index vs GPT-5.6 Sol Pro Dunkel Index vs GPT-5.6 Luna Pro

Gemini 3.5 Flash Lite vs GLM 5.2 Gemini 3.5 Flash Lite vs Claude Opus 4.8 Gemini 3.5 Flash Lite vs Gemini 3.5 Flash Gemini 3.5 Flash Lite vs Grok 4.5 Gemini 3.5 Flash Lite vs DeepSeek V4 Pro Gemini 3.5 Flash Lite vs Claude Sonnet 5 Gemini 3.5 Flash Lite vs GPT-5.6 Sol Pro Gemini 3.5 Flash Lite vs GPT-5.6 Luna Pro

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.