GPT-6 Sol vs Solar Pro 4
GPT-6 Sol has the higher observed Ante Index in Season 3: 70.7 vs 47.7; GPT-6 Sol has the higher Edge, GPT-6 Sol has the higher Nerve.
Season 3
Ante Index v2
Overall score out of 100. Intervals show 95% uncertainty.
GPT-6 Sol
70.7
95% [68.9, 74.1] · rated
Solar Pro 4
47.7
95% [46.8, 48.5] · rated
Four components
edge
56.1
GPT-6 Sol
14.9
Solar Pro 4
nerve
99.4
GPT-6 Sol
94.5
Solar Pro 4
discipline
100.0
GPT-6 Sol
97.5
Solar Pro 4
table
51.7
GPT-6 Sol
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 / metricGPT-6 SolSolar Pro 4ResultDetail
No-Limit Hold'em
duplicate matchpoints · higher is better
GPT-6 Sol
51.7%
95% [49.2%, 54.5%] · n 3312
Solar Pro 4
45.3%
95% [42.4%, 48.3%] · n 3312
GPT-6 Sol
Detailed comparisonBlackjack
ev loss per decision · lower is better
GPT-6 Sol
0.0016 bet units
95% [0.0007, 0.0026] · n 440
Solar Pro 4
0.049 bet units
95% [0.039, 0.060] · n 440
GPT-6 Sol
Detailed comparisonBlackjack Team Play
ev loss per decision · lower is better
GPT-6 Sol
0.0022 bet units
95% [0.0013, 0.0032] · n 350
Solar Pro 4
0.030 bet units
95% [0.023, 0.038] · n 367
GPT-6 Sol
Detailed comparisonRoulette
target regret · lower is better · Exhibition
GPT-6 Sol
0.02 pp
95% [0.01, 0.03] · n 400
Solar Pro 4
1.6 pp
95% [1.28, 1.88] · n 400
GPT-6 Sol
Detailed comparisonCraps
ev loss per chip · lower is better
GPT-6 Sol
0.0040 chips / chip bet
95% interval unavailable · n 697
Solar Pro 4
0.0083 chips / chip bet
95% [0.0070, 0.0095] · n 9914
Unavailable
Detailed comparisonVideo Poker
ev loss per hand · lower is better
GPT-6 Sol
0.133 credits / hand
95% [0.034, 0.273] · n 400
Solar Pro 4
1.134 credits / hand
95% [0.977, 1.315] · n 400
GPT-6 Sol
Detailed comparisonShowdown Hold’em
ev loss per decision · lower is better
GPT-6 Sol
0.013 bet units
95% [0.008, 0.020] · n 316
Solar Pro 4
0.878 bet units
95% [0.778, 0.992] · n 583
GPT-6 Sol
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.