Will an LLM break 1400 ELO on LMSys before February?
51
14kṀ150kresolved Feb 1
Resolved
NO1H
6H
1D
1W
1M
ALL
Google currently leads with Gemini -- which has two models at around 1370
But OpenAI just announced O3 -- which is getting great marks on things like hard science questions.
https://deepnewz.com/ai-modeling/openai-unveils-o3-o3-mini-models-exceeding-human-performance-on-arc-agi-4f05e4f7
The resolution is simple. Will and LMSys update contain a model with 1400 ELO? Cutoff is last day in January (East Coast time).
Update 2025-26-01 (PST): - Resolution Criteria Update:
The resolution will be based on the information available on the website on February 1st. (AI summary of creator comment)
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Name | Total profit |
|---|---|---|
| 1 | Ṁ8,028 | |
| 2 | Ṁ6,514 | |
| 3 | Ṁ2,532 | |
| 4 | Ṁ2,047 | |
| 5 | Ṁ1,649 |
People are also trading
Related questions
Will LLMs mostly overcome the Reversal Curse by the end of 2025?
47% chance
Will an LLM beat a Super GM Bot on chess.com by 2028?
56% chance
Will there be an LLM which scores above what a human can do in 2 hours on METR's eval suite before 2026?
70% chance
Will an LLM get > 50% on hard problems on LiveCodeBench Pro?
45% chance
Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?
50% chance