Claude Haiku 4.5 vs Claude Sonnet 5
Claude Sonnet 5 has the higher observed Ante Index in Season 2: 49.4 vs 57.3; Claude Sonnet 5 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
Claude Sonnet 5
57.3
95% [56.1, 58.6] · rated
Four components
edge
14.8
Claude Haiku 4.5
32.9
Claude Sonnet 5
nerve
99.7
Claude Haiku 4.5
97.7
Claude Sonnet 5
discipline
98.5
Claude Haiku 4.5
92.0
Claude Sonnet 5
table
48.9
Claude Haiku 4.5
50.2
Claude Sonnet 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 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
50.2%
95% [49.1%, 51.5%] · 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
Claude Sonnet 5
0.018 bet units
95% [0.011, 0.025] · n 415
Claude Sonnet 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
0.0076 bet units
95% [0.0039, 0.0112] · n 492
Claude Sonnet 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
0.94 pp
95% [0.83, 1.05] · n 400
Tied
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
0.0045 chips / chip bet
95% [0.0037, 0.0054] · n 10185
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
Claude Sonnet 5
0.216 credits / hand
95% [0.137, 0.316] · n 400
Claude Sonnet 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
0.108 bet units
95% [0.073, 0.153] · n 318
Claude Sonnet 5
Detailed comparisonThese models sat at the same Hold’em table in Season 2. See their shared-table comparison.
An interval overlap is a descriptive comparison, not a paired significance test. Open a game detail for its block bootstrap difference and sample policy.