DeepSeek V4.1 Flash vs Solar Pro 4
DeepSeek V4.1 Flash has the higher observed Ante Index in Season 3: 59.4 vs 47.7; DeepSeek V4.1 Flash has the higher Edge, Solar Pro 4 has the higher Discipline.
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
Solar Pro 4
47.7
95% [46.8, 48.5] · rated
Four components
edge
36.3
DeepSeek V4.1 Flash
14.9
Solar Pro 4
nerve
98.8
DeepSeek V4.1 Flash
94.5
Solar Pro 4
discipline
92.7
DeepSeek V4.1 Flash
97.5
Solar Pro 4
table
50.7
DeepSeek V4.1 Flash
44.6
Solar Pro 4
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 FlashSolar Pro 4ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
DeepSeek V4.1 Flash
50.7%
95% [48.1%, 53.2%] · n 3312
Solar Pro 4
45.3%
95% [42.4%, 48.3%] · 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
Solar Pro 4
0.049 bet units
95% [0.039, 0.060] · n 440
DeepSeek V4.1 Flash
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
Solar Pro 4
0.030 bet units
95% [0.023, 0.038] · n 367
DeepSeek V4.1 Flash
Detailed comparisonRoulette
target regret · lower is better · Exhibition
DeepSeek V4.1 Flash
0.68 pp
95% [0.56, 0.82] · n 400
Solar Pro 4
1.6 pp
95% [1.28, 1.88] · n 400
DeepSeek V4.1 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
Solar Pro 4
0.0083 chips / chip bet
95% [0.0070, 0.0095] · n 9914
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
Solar Pro 4
1.134 credits / hand
95% [0.977, 1.315] · n 400
DeepSeek V4.1 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
Solar Pro 4
0.878 bet units
95% [0.778, 0.992] · n 583
DeepSeek V4.1 Flash
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.