This market is closed and no longer accepting bets.
185
Comments
5
Markets
0
Comments per hour
Comments
TheGuro
6 months ago
It's Gemini or Claude (if they decide to release Opus in the next two weeks). Google keeps releasing experimental models of Gemini that hits the leaderboards, it's number 1 for quite some time.
thx4urdonation
5 months ago
Not looking good for bussyblaster. He's getting his bussy blasted.
AxelBlues
6 months ago
I hate Google but Gemini will win
TheGuro
5 months ago
I really appreciate the cheap shares. First, the o1 is a 'thinking' model, it's designed for deep reasoning and complex problem-solving, it does a really good job in this area. It's not a match for Gemini 1206 if you look at the performance across a wide range of benchmarks. Second, o1 is actually a regression for o1-preview, o1-preview is more similar to the o1-pro model. Third and most important - you will learn in the hard way what it means to buy into a market without doing deep research into its subject. gl
WELLWELLWELL
5 months ago
Just got o1 multiple times in lmarena, it completely destroyed the other models, its joever for the gemini idiots, loading up shares now, fill me
predictordeniz
5 months ago
o1 has less compute time than o1-preview. The real o1 model is actually o1 pro without compute time limitations. The fact that people don’t understand this actually scares me.
TheGuro
5 months ago
Do you even know how the leaderboard in lmarena is calculated? It’s based on votes gathered by dumb users asking dumb questions in a very short conversation with 2 anonymous bots. They are not solving PhD math equations. That's the only reason Gemini keeps winning, and that's why o1-preview is only ranked 5.
SpazMoneys
6 months ago
OpenAI told me they have released in their toilet and named it royvanrijn
royvanrijn
6 months ago
Gemini has already released their new model, OpenAI is still going to release something in their 12 days....
thx4urdonation
6 months ago
gemini should be at 85-90%.
Dontnowhoitis
6 months ago
If two models are tied for the top arena score at this market's check time, resolution will be based on whichever model's name, as it is described in this market group, comes first in alphabetical order (e.g. if both were tied, Claude would resolve to "Yes", and "Gemini would resolve to "No").
TheGuro
6 months ago
12 days left, Gemini is not going anywhere soon. The only company that can actually pull something off is Anthropic, will they release Claude Opus in the next week? who knows.