Claude Haiku 5.5 vs Claude Sonnet 5.5
Claude Sonnet 5.5 has the higher observed Ante Index in Season 3: 59.4 vs 67.5; Claude Sonnet 5.5 has the higher Edge, Claude Haiku 5.5 has the higher Nerve.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
Claude Haiku 5.5
59.4
95% [58.1, 60.9] · rated
Claude Sonnet 5.5
67.5
95% [66.2, 69.7] · rated
Four components
edge
35.7
Claude Haiku 5.5
49.7
Claude Sonnet 5.5
nerve
99.7
Claude Haiku 5.5
99.3
Claude Sonnet 5.5
discipline
99.5
Claude Haiku 5.5
100.0
Claude Sonnet 5.5
table
44.6
Claude Haiku 5.5
52.1
Claude Sonnet 5.5
By game
Each row uses the published headline metric in Season 3. “Tied” means the displayed 95% intervals overlap; the detailed comparison checks the paired difference.
Game / metricClaude Haiku 5.5Claude Sonnet 5.5ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Haiku 5.5
44.6%
95% [41.3%, 47.7%] · n 3312
Claude Sonnet 5.5
52.4%
95% [49.9%, 55.0%] · n 3312
Claude Sonnet 5.5
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Haiku 5.5
0.012 bet units
95% [0.006, 0.019] · n 429
Claude Sonnet 5.5
0.0022 bet units
95% [0.0010, 0.0036] · n 436
Claude Sonnet 5.5
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Haiku 5.5
0.012 bet units
95% [0.002, 0.026] · n 340
Claude Sonnet 5.5
0.0097 bet units
95% [0.005, 0.015] · n 338
Tied
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Haiku 5.5
0.12 pp
95% [0.09, 0.17] · n 400
Claude Sonnet 5.5
0.09 pp
95% [0.04, 0.14] · n 400
Tied
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Haiku 5.5
0.0048 chips / chip bet
95% [0.0037, 0.0060] · n 2597
Claude Sonnet 5.5
0.0038 chips / chip bet
95% [0.0028, 0.0051] · n 2643
Tied
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Haiku 5.5
0.287 credits / hand
95% [0.228, 0.355] · n 400
Claude Sonnet 5.5
0.066 credits / hand
95% [0.031, 0.108] · n 400
Claude Sonnet 5.5
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Haiku 5.5
0.081 bet units
95% [0.048, 0.124] · n 332
Claude Sonnet 5.5
0.023 bet units
95% [0.012, 0.035] · n 307
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.