Claude Haiku 4.5 vs Claude Mythos 5.1
Claude Mythos 5.1 has the higher observed Ante Index in Season 3: 48.6 vs 72.2; Claude Mythos 5.1 has the higher Edge, Claude Mythos 5.1 has the higher Nerve.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
Claude Haiku 4.5
48.6
95% [47.8, 49.3] · rated
Claude Mythos 5.1
72.2
95% [70.4, 75.8] · rated
Four components
edge
15.1
Claude Haiku 4.5
58.9
Claude Mythos 5.1
nerve
98.6
Claude Haiku 4.5
99.5
Claude Mythos 5.1
discipline
98.7
Claude Haiku 4.5
99.8
Claude Mythos 5.1
table
43.5
Claude Haiku 4.5
52.8
Claude Mythos 5.1
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 Haiku 4.5Claude Mythos 5.1ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
Claude Haiku 4.5
44.4%
95% [42.3%, 46.7%] · n 3456
Claude Mythos 5.1
52.3%
95% [49.5%, 55.1%] · n 3456
Claude Mythos 5.1
Detailed comparisonBlackjack
ev loss per decision · lower is better
Claude Haiku 4.5
0.055 bet units
95% [0.044, 0.067] · n 397
Claude Mythos 5.1
0.0016 bet units
95% [0.0008, 0.0026] · n 440
Claude Mythos 5.1
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
Claude Haiku 4.5
0.045 bet units
95% [0.036, 0.054] · n 329
Claude Mythos 5.1
0.0022 bet units
95% [0.0012, 0.0032] · n 347
Claude Mythos 5.1
Detailed comparisonRoulette
target regret · lower is better · Exhibition
Claude Haiku 4.5
1.3 pp
95% [1.04, 1.51] · n 400
Claude Mythos 5.1
0.12 pp
95% [0.06, 0.18] · n 400
Claude Mythos 5.1
Detailed comparisonCraps
ev loss per chip · lower is better
Claude Haiku 4.5
0.0078 chips / chip bet
95% [0.0063, 0.0093] · n 5473
Claude Mythos 5.1
0.0039 chips / chip bet
95% [0.0030, 0.0050] · n 5497
Claude Mythos 5.1
Detailed comparisonVideo Poker
ev loss per hand · lower is better
Claude Haiku 4.5
1.200 credits / hand
95% [0.978, 1.452] · n 400
Claude Mythos 5.1
0.023 credits / hand
95% [0.002, 0.054] · n 400
Claude Mythos 5.1
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
Claude Haiku 4.5
0.597 bet units
95% [0.509, 0.680] · n 454
Claude Mythos 5.1
0.0074 bet units
95% [0.001, 0.015] · n 316
Claude Mythos 5.1
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.