Claude Opus 5.5 vs DeepSeek V4.1 Flash
Claude Opus 5.5 has the higher observed Ante Index in Season 3: 74.9 vs 59.4; Claude Opus 5.5 has the higher Edge, Claude Opus 5.5 has the higher Nerve.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
Claude Opus 5.5
74.9
95% [72.6, 78.0] · rated
DeepSeek V4.1 Flash
59.4
95% [57.9, 61.8] · rated
Four components
edge
63.1
Claude Opus 5.5
36.3
DeepSeek V4.1 Flash
nerve
99.6
Claude Opus 5.5
98.8
DeepSeek V4.1 Flash
discipline
100.0
Claude Opus 5.5
92.7
DeepSeek V4.1 Flash
table
56.1
Claude Opus 5.5
50.7
DeepSeek V4.1 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 Opus 5.5DeepSeek V4.1 FlashResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Opus 5.5
55.2%
95% [51.9%, 58.7%] · n 3312
DeepSeek V4.1 Flash
50.7%
95% [48.1%, 53.2%] · n 3312
Tied
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Opus 5.5
0.0021 bet units
95% [0.0011, 0.0032] · n 436
DeepSeek V4.1 Flash
0.0052 bet units
95% [0.0027, 0.0085] · n 430
Tied
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Opus 5.5
0.0027 bet units
95% [0.0015, 0.0041] · n 347
DeepSeek V4.1 Flash
0.010 bet units
95% [0.004, 0.018] · n 328
Claude Opus 5.5
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Opus 5.5
0.03 pp
95% [0.02, 0.04] · n 400
DeepSeek V4.1 Flash
0.68 pp
95% [0.56, 0.82] · n 400
Claude Opus 5.5
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Opus 5.5
0.0056 chips / chip bet
95% [0.0045, 0.0069] · n 8391
DeepSeek V4.1 Flash
0.0057 chips / chip bet
95% [0.0043, 0.0073] · n 5546
Tied
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Opus 5.5
0.022 credits / hand
95% [0.002, 0.063] · n 400
DeepSeek V4.1 Flash
0.740 credits / hand
95% [0.607, 0.886] · n 400
Claude Opus 5.5
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Opus 5.5
0.0005 bet units
95% [0.0000, 0.0014] · n 313
DeepSeek V4.1 Flash
0.067 bet units
95% [0.025, 0.120] · n 324
Claude Opus 5.5
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.