DeepSeek V4.1 Flash vs Gemini 3.8 Flash
Gemini 3.8 Flash has the higher observed Ante Index in Season 3: 59.4 vs 73.6; Gemini 3.8 Flash has the higher Edge, DeepSeek V4.1 Flash has the higher Table.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
DeepSeek V4.1 Flash
59.4
95% [57.9, 61.8] · rated
Gemini 3.8 Flash
73.6
95% [72.1, 75.7] · rated
Four components
edge
36.3
DeepSeek V4.1 Flash
62.1
Gemini 3.8 Flash
nerve
98.8
DeepSeek V4.1 Flash
99.9
Gemini 3.8 Flash
discipline
92.7
DeepSeek V4.1 Flash
100.0
Gemini 3.8 Flash
table
50.7
DeepSeek V4.1 Flash
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 / metricDeepSeek V4.1 FlashGemini 3.8 FlashResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
DeepSeek V4.1 Flash
50.7%
95% [48.1%, 53.2%] · 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
DeepSeek V4.1 Flash
0.0052 bet units
95% [0.0027, 0.0085] · n 430
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
DeepSeek V4.1 Flash
0.010 bet units
95% [0.004, 0.018] · n 328
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
DeepSeek V4.1 Flash
0.68 pp
95% [0.56, 0.82] · n 400
Gemini 3.8 Flash
0.20 pp
95% [0.16, 0.24] · n 400
Gemini 3.8 Flash
Detailed comparisonCraps
ev loss per chip · lower is better
DeepSeek V4.1 Flash
0.0057 chips / chip bet
95% [0.0043, 0.0073] · n 5546
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
DeepSeek V4.1 Flash
0.740 credits / hand
95% [0.607, 0.886] · 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
DeepSeek V4.1 Flash
0.067 bet units
95% [0.025, 0.120] · n 324
Gemini 3.8 Flash
0.022 bet units
95% [0.015, 0.030] · n 338
Tied
Detailed comparisonThese models sat at the same Hold’em table in Season 3. 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.