Claude Haiku 4.5 vs Claude Sonnet 5.5
Claude Sonnet 5.5 has the higher observed Ante Index in Season 2: 49.4 vs 67.6; Claude Sonnet 5.5 has the higher Edge, Claude Sonnet 5.5 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
Claude Sonnet 5.5
67.6
95% [66.4, 69.5] · rated
Four components
edge
14.8
Claude Haiku 4.5
49.9
Claude Sonnet 5.5
nerve
99.7
Claude Haiku 4.5
100.0
Claude Sonnet 5.5
discipline
98.5
Claude Haiku 4.5
99.8
Claude Sonnet 5.5
table
48.9
Claude Haiku 4.5
51.6
Claude Sonnet 5.5
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 4.5Claude Sonnet 5.5ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Haiku 4.5
49.2%
95% [47.7%, 50.6%] · n 28800
Claude Sonnet 5.5
51.5%
95% [49.2%, 53.9%] · n 28800
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
Claude Sonnet 5.5
0.0044 bet units
95% [0.0022, 0.0070] · n 466
Claude Sonnet 5.5
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
Claude Sonnet 5.5
0.0077 bet units
95% [0.0030, 0.0128] · n 214
Claude Sonnet 5.5
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Haiku 4.5
0.99 pp
95% [0.82, 1.15] · n 400
Claude Sonnet 5.5
0.14 pp
95% [0.08, 0.22] · n 400
Claude Sonnet 5.5
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
Claude Sonnet 5.5
0.0032 chips / chip bet
95% interval unavailable · n 1219
Unavailable
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
Claude Sonnet 5.5
0.075 credits / hand
95% [0.036, 0.130] · n 400
Claude Sonnet 5.5
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
Claude Sonnet 5.5
0.017 bet units
95% [0.009, 0.028] · n 312
Claude Sonnet 5.5
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.