Claude Haiku 4.5 vs Grok 4.7
Grok 4.7 has the higher observed Ante Index in Season 2: 49.4 vs 52.6; Grok 4.7 has the higher Edge, Claude Haiku 4.5 has the higher Nerve.
Season 2
Ante Index v1
Overall score out of 100. Intervals show 95% uncertainty.
Claude Haiku 4.5
49.4
95% [48.6, 50.0] · rated
Grok 4.7
52.6
95% [51.4, 53.6] · rated
Four components
edge
14.8
Claude Haiku 4.5
28.0
Grok 4.7
nerve
99.7
Claude Haiku 4.5
98.6
Grok 4.7
discipline
98.5
Claude Haiku 4.5
75.0
Grok 4.7
table
48.9
Claude Haiku 4.5
51.0
Grok 4.7
By game
Each row uses the published headline metric in Season 2. “Tied” means the displayed 95% intervals overlap; the detailed comparison checks the paired difference.
Game / metricClaude Haiku 4.5Grok 4.7ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Haiku 4.5
49.2%
95% [47.7%, 50.6%] · n 28800
Grok 4.7
51.0%
95% [49.8%, 52.2%] · n 54720
Tied
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Haiku 4.5
0.064 bet units
95% [0.051, 0.077] · n 418
Grok 4.7
0.0027 bet units
95% [0.0015, 0.0041] · n 443
Grok 4.7
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Haiku 4.5
0.042 bet units
95% [0.031, 0.053] · n 334
Grok 4.7
0.014 bet units
95% [0.008, 0.021] · n 456
Grok 4.7
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Haiku 4.5
0.99 pp
95% [0.82, 1.15] · n 400
Grok 4.7
1.6 pp
95% [1.48, 1.72] · n 400
Claude Haiku 4.5
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Haiku 4.5
0.0050 chips / chip bet
95% [0.0043, 0.0059] · n 6967
Grok 4.7
0.0040 chips / chip bet
95% [0.0031, 0.0053] · n 5621
Tied
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Haiku 4.5
1.220 credits / hand
95% [1.025, 1.468] · n 400
Grok 4.7
1.804 credits / hand
95% [1.633, 1.972] · n 400
Claude Haiku 4.5
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Haiku 4.5
0.590 bet units
95% [0.508, 0.684] · n 451
Grok 4.7
0.585 bet units
95% [0.480, 0.688] · n 376
Tied
Detailed comparisonAn interval overlap is a descriptive comparison, not a paired significance test. Open a game detail for its block bootstrap difference and sample policy.