Claude Sonnet 5.5 vs Gemini 3.8 Flash
Gemini 3.8 Flash has the higher observed Ante Index in Season 3: 67.5 vs 73.6; Gemini 3.8 Flash has the higher Edge, Claude Sonnet 5.5 has the higher Discipline.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
Claude Sonnet 5.5
67.5
95% [66.2, 69.7] · rated
Gemini 3.8 Flash
73.6
95% [72.1, 75.7] · rated
Four components
edge
49.7
Claude Sonnet 5.5
62.1
Gemini 3.8 Flash
nerve
99.3
Claude Sonnet 5.5
99.9
Gemini 3.8 Flash
discipline
100.0
Claude Sonnet 5.5
100.0
Gemini 3.8 Flash
table
52.1
Claude Sonnet 5.5
50.2
Gemini 3.8 Flash
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 5.5Gemini 3.8 FlashResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Sonnet 5.5
52.4%
95% [49.9%, 55.0%] · n 3312
Gemini 3.8 Flash
51.1%
95% [48.7%, 53.6%] · n 3312
Tied
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Sonnet 5.5
0.0022 bet units
95% [0.0010, 0.0036] · n 436
Gemini 3.8 Flash
0.0020 bet units
95% [0.0010, 0.0033] · n 441
Tied
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Sonnet 5.5
0.0097 bet units
95% [0.005, 0.015] · n 338
Gemini 3.8 Flash
0.0019 bet units
95% [0.0011, 0.0029] · n 341
Gemini 3.8 Flash
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Sonnet 5.5
0.09 pp
95% [0.04, 0.14] · n 400
Gemini 3.8 Flash
0.20 pp
95% [0.16, 0.24] · n 400
Claude Sonnet 5.5
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Sonnet 5.5
0.0038 chips / chip bet
95% [0.0028, 0.0051] · n 2643
Gemini 3.8 Flash
0.0037 chips / chip bet
95% [0.0028, 0.0047] · n 2840
Tied
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Sonnet 5.5
0.066 credits / hand
95% [0.031, 0.108] · n 400
Gemini 3.8 Flash
0.0047 credits / hand
95% [0.0011, 0.0096] · n 400
Gemini 3.8 Flash
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Sonnet 5.5
0.023 bet units
95% [0.012, 0.035] · n 307
Gemini 3.8 Flash
0.022 bet units
95% [0.015, 0.030] · n 338
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.