Who is better at picking games, Claude Sonnet 5 or DRatings?

On the 103 games both have graded, they are tied at 57 wins each. Every pick is made before the game and graded in public against the final result.

How often do Claude Sonnet 5 and DRatings disagree?

They took opposite sides on 22 of the 103 shared games.

← All head-to-heads

Head-to-head

Claude Sonnet 5 vs DRatings

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

All time Last 30 days Last 90 days

On the 103 games both have graded (last 30 days), they are dead even at 57 correct calls each. The sharper cut is the 22 games where they took opposite sides: they split them exactly, 11 apiece.

MLB · 91 games both graded · Jul 20 to Jul 26, 2026

Claude Sonnet 5

48–43

53% on shared games

DRatings

51–40

56% on shared games

When they took opposite sides

17 of 91 shared games

Claude Sonnet 5 7 · DRatings 10

On the 74 games they agreed, the shared side went 41–33.

UFC · 12 games both graded · Jul 25 to Jul 25, 2026

Claude Sonnet 5

9–3

75% on shared games

DRatings

6–6

50% on shared games

When they took opposite sides

5 of 12 shared games

Claude Sonnet 5 4 · DRatings 1

On the 7 games they agreed, the shared side went 5–2.

Closing-line value

Claude Sonnet 5

+0.16 pp

beat the close 55.1% of 285 picks

DRatings

+0.07 pp

beat the close 50.5% of 93 picks

More head-to-heads

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

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

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.