GPT-5.6 Terra vs GPT-6 Astra
GPT-6 Astra has the higher observed Ante Index in Season 3: 59.4 vs 87.5; GPT-6 Astra has the higher Edge, GPT-5.6 Terra has the higher Table.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
GPT-5.6 Terra
59.4
95% [58.2, 60.9] · rated
GPT-6 Astra
87.5
95% [85.6, 88.9] · rated
Four components
edge
33.0
GPT-5.6 Terra
89.3
GPT-6 Astra
nerve
98.7
GPT-5.6 Terra
100.0
GPT-6 Astra
discipline
99.4
GPT-5.6 Terra
100.0
GPT-6 Astra
table
55.2
GPT-5.6 Terra
52.1
GPT-6 Astra
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 / metricGPT-5.6 TerraGPT-6 AstraResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
GPT-5.6 Terra
56.3%
95% [53.8%, 58.8%] · n 3456
GPT-6 Astra
52.5%
95% [50.3%, 54.9%] · n 3312
Tied
Detailed comparisonBlackjack
ev loss per decision · lower is better
GPT-5.6 Terra
0.019 bet units
95% [0.011, 0.028] · n 436
GPT-6 Astra
0.0017 bet units
95% [0.0009, 0.0027] · n 438
GPT-6 Astra
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
GPT-5.6 Terra
0.0047 bet units
95% [0.0025, 0.0076] · n 352
GPT-6 Astra
0.0021 bet units
95% [0.0012, 0.0031] · n 342
Tied
Detailed comparisonRoulette
target regret · lower is better · Exhibition
GPT-5.6 Terra
0.32 pp
95% [0.24, 0.41] · n 400
GPT-6 Astra
0.01 pp
95% [0, 0.01] · n 400
GPT-6 Astra
Detailed comparisonCraps
ev loss per chip · lower is better
GPT-5.6 Terra
0.0082 chips / chip bet
95% [0.0071, 0.0095] · n 11432
GPT-6 Astra
Unavailable
95% interval unavailable · n 0
Unavailable
Detailed comparisonVideo Poker
ev loss per hand · lower is better
GPT-5.6 Terra
0.175 credits / hand
95% [0.116, 0.254] · n 400
GPT-6 Astra
0.0006 credits / hand
95% [0.0000, 0.0013] · n 400
GPT-6 Astra
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
GPT-5.6 Terra
0.077 bet units
95% [0.049, 0.113] · n 312
GPT-6 Astra
0.0003 bet units
95% [0.0000, 0.0008] · n 314
GPT-6 Astra
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.