Before February 2025, will a Gemini model exceed Claude 3.5 Sonnet 10/22's Global Average score on Simple Bench?
11
100Ṁ522
resolved Feb 5
Resolved
NO

https://simple-bench.com/ Claude 3.5 Sonnet 10/22 achieves 41.4% whereas the best Gemini model scores 27.1%

SimpleBench
SimpleBench

  • Update 2025-22-01 (PST): - Resolution Date: The market will now be resolved on February 1st, 2025 instead of the previously stated date. (AI summary of creator comment)

LLMs
Math
GPT-4
New Year's Resolutions 2025
Google Gemini
Get
Ṁ1,000
to start trading!

🏅 Top traders

#NameTotal profit
1Ṁ116
2Ṁ46
3Ṁ27
Sort by:

@JaundicedBaboon Time to resolve? It's already February everywhere.

bought Ṁ50 YES

Can we go ahead and resolve this one?

@rogs Won't resolve it until February 1st

bought Ṁ5 NO

Now I'm looking at my comment above and wondering what I was thinking. Did I think this was a post about OpenAI models vs Claude rather than about Gemini vs Claude? Why did I think it was resolvable already?

Related questions

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules