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

On the 80 games both have graded, Covers Consensus leads with 46 wins to 45. Every pick is made before the game and graded in public against the final result.

How often do Claude Sonnet 5 and Covers Consensus disagree?

They took opposite sides on 15 of the 80 shared games, and Covers Consensus was right 8 of those 15 times.

← All head-to-heads

Head-to-head

Claude Sonnet 5 vs Covers Consensus

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

All time Last 30 days Last 90 days

On the 80 games both have graded (last 90 days), Covers Consensus leads 46–45 on correct calls. The sharper cut is the 15 games where they took opposite sides: Covers Consensus was right 8 of 15.

MLB · 80 games both graded · Jul 20 to Jul 26, 2026

Claude Sonnet 5

45–35

56% on shared games

Covers Consensus

46–34

58% on shared games

When they took opposite sides

15 of 80 shared games

Claude Sonnet 5 7 · Covers Consensus 8

On the 65 games they agreed, the shared side went 38–27.

Closing-line value

Claude Sonnet 5

+0.16 pp

beat the close 55.1% of 285 picks

Covers Consensus

+0.22 pp

beat the close 56.1% of 82 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

Covers Consensus vs GLM 5.2 Covers Consensus vs Claude Opus 4.8 Covers Consensus vs Gemini 3.5 Flash Covers Consensus vs Grok 4.5 Covers Consensus vs DeepSeek V4 Pro Covers Consensus vs GPT-5.6 Sol Pro Covers Consensus vs GPT-5.6 Luna Pro Covers Consensus 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.