jazarwil
jazarwil on Hacker News
I'd love to run more games, just very expensive unfortunately.
Wdym exactly? I ran 163 games, are you suggesting more games or something else?
There are a few reasons that come to mind, such as winning larger pots on average, and also playing more hands by virtue of not getting knocked out as frequently.
Oh to be clear, there are ~21k hands here, and far more decisions than that.
I didn't incorporate any open weights/source models just to limit the number of API providers I had to juggle, but it is just a config change if somebody wants to try a run with them.
Not at the moment, do you have something in mind?
I've seen some theories tossed around but I don't think I'm qualified to offer an authoritative answer. Gemini 3 Pro specifically seems to be consistently "tighter" and more passive than Flash.
It greatly depends on the models. The 6-handed setup with Opus and Pro cost about $30/game. The 4-handed setup with just small models was $6/game. I'd love to run more but I already spent quite a bit as it is.
Posted by
jazarwil on Thursday January 08, 2026 @08:37AM
from the show-hn dept.
https://pokerbench.adfontes.io/run/Large_Models
PokerBench is my attempt at a new LLM benchmark wherein frontier models play Texas Hold'em in an arena setting. It also features a simulator to view individual games and observe how the different models reason about poker strategy. Opus/Haiku, Gemini Pro/Flash, GPT-5.2/5 mini, and Grok 4.1 Fast Reasoning have all been included.All code -> https://github.com/JoeAzar/pokerbench
You cannot compare GPT 4 to Gemini Pro. They are different classes of models.
What exactly do you think you saw? Bard is not trained on any data of that nature, unless it is already publicly available.