Will an LLM with less than 10B parameters beat GPT4 by EOY 2025?
8
39
Ṁ295Ṁ260
2026
84%
chance
1D
1W
1M
ALL
How much juice is left in 10B parameters?
the original GPT4-0314 (ELO 1188)
judged by Lmsys Arena Leaderboard
current SoTA: Llama 3 8B instruct (1147)
maybe Phi-3 small?
Get Ṁ200 play money
Sort by:
@singer There is a without refusal board on lmsys. The disparity between main and that is how much advantages not having censorship’s give u
Related questions
Will the best LLM in 2027 have <1 trillion parameters?
29% chance
Will the best LLM in 2025 have <500 billion parameters?
32% chance
Will the best LLM in 2026 have <1 trillion parameters?
44% chance
Will the best LLM in 2026 have <500 billion parameters?
27% chance
Will there be 20+ LLMs that match or outperform GPT-3.5's performance by the end of 2024?
89% chance
Will there be an open source LLM as good as GPT4 by June 2024?
39% chance
Will an open-source LLM beat or match GPT-4 by the end of 2024?
64% chance
Will the best LLM in 2027 have <250 billion parameters?
12% chance
Will an LLM (a GPT-like text AI) defeat the World Champion at Chess before 2035?
47% chance