GPT 4.5 "Intelligence" via artificialanalysis.ai
19
100Ṁ1621
resolved May 9
100%99.0%
50-54 (at or below o1-mini)
0.3%
<50 (underwhelming)
0.3%
55-59 (worse than Deepseek R1)
0.2%
60-64 (matches SoTA reasoning models)
0.2%
65+ (new frontier)

In May 2024, Orion (GPT-4.5, assumed to be GPT-5 at the time) was promised to be a Whale by Microsoft.

Will it surpass the current whale (Deepseek R1)?

Source: https://artificialanalysis.ai (subject to some discretion in case the methodology changes)

Get
Ṁ1,000
to start trading!

🏅 Top traders

#NameTotal profit
1Ṁ62
2Ṁ54
3Ṁ43
4Ṁ25
5Ṁ15
Sort by:
bought Ṁ523 YES

Just resolved now, was waiting for it to be independently benchmark but I guess it's too expensive and openAI admits 4.5 is lower than 4.1 on technical benchmarks.

bought Ṁ1 YES

Assuming it's not a reasoning model is 60 a fair upper limit?

Or does OpenAI have something up their sleeves to one up Grok 3 (~53 w/o reasoning, ~66 w/ reasoning)

Since there's over 50% for this to resolve to the highest option I added more

https://manifold.markets/ChinmayTheMathGuy/gpt-45-intelligence-via-artificiala-u8ZOQuAhOZ

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules