Claude Sonnet 5 vs GPT-6 Luna
GPT-6 Luna has the higher observed Ante Index in Season 3: 55.4 vs 66.1; GPT-6 Luna has the higher Edge, Claude Sonnet 5 has the higher Table.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
Claude Sonnet 5
55.4
95% [54.4, 56.6] · rated
GPT-6 Luna
66.1
95% [64.5, 68.6] · rated
Four components
edge
28.5
Claude Sonnet 5
48.1
GPT-6 Luna
nerve
98.6
Claude Sonnet 5
99.5
GPT-6 Luna
discipline
94.5
Claude Sonnet 5
99.8
GPT-6 Luna
table
48.6
Claude Sonnet 5
47.6
GPT-6 Luna
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 Sonnet 5GPT-6 LunaResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Sonnet 5
48.2%
95% [45.8%, 50.6%] · n 3312
GPT-6 Luna
47.7%
95% [44.8%, 50.7%] · n 3312
Tied
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Sonnet 5
0.022 bet units
95% [0.014, 0.030] · n 411
GPT-6 Luna
0.0018 bet units
95% [0.0009, 0.0028] · n 438
GPT-6 Luna
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Sonnet 5
0.017 bet units
95% [0.008, 0.030] · n 316
GPT-6 Luna
0.0020 bet units
95% [0.0010, 0.0032] · n 338
GPT-6 Luna
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Sonnet 5
0.62 pp
95% [0.52, 0.74] · n 400
GPT-6 Luna
0.78 pp
95% [0.64, 0.93] · n 400
Tied
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Sonnet 5
0.0070 chips / chip bet
95% [0.0059, 0.0080] · n 12201
GPT-6 Luna
0.0086 chips / chip bet
95% interval unavailable · n 809
Unavailable
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Sonnet 5
0.217 credits / hand
95% [0.143, 0.304] · n 400
GPT-6 Luna
0.356 credits / hand
95% [0.181, 0.568] · n 400
Tied
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Sonnet 5
0.092 bet units
95% [0.057, 0.137] · n 322
GPT-6 Luna
0.052 bet units
95% [0.032, 0.075] · n 329
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.