Will OpenAI Release a Model Capable of Reliably performing Gradeschool Math from Reasoning by Jan 1, 2025?
Basic
35
Ṁ1.2k2025
73%
chance
1D
1W
1M
ALL
I.e. will a "Q*" model be released?
Get Ṁ600 play money
Related questions
Sort by:
@Luca3f84 fair, but given this subjective criteria I will challenge any YES resolution is the success rate is below 90%, there are obvious consistent blind spots, or Manifold poll will show majority says it is not reliable
@0482 completely fair. I would do the same. Fwiw, the way the question is worded, it excludes the use of code interpreter, mere interpretation from vision etc.
Related questions
Related questions
Will AI be able to solve confusing but elementary geometric reasoning problems in 2024?
30% chance
Will an AI solve any important mathematical conjecture before January 1st, 2030?
75% chance
Will OpenAI's next-gen math-focused model score at least 95% on the MATH benchmark?
71% chance
Will OpenAI release GPT-5 before the end of 2024?
43% chance
Will any language model trained without large number arithmetic be able to generalize to large number arithmetic by 2026?
52% chance
Will OpenAI release an AI product with a cool name by Jan 1, 2025?
31% chance
Will OpenAI release GPT-5 before the end of 2024?
44% chance
Will OpenAI release a technical report on a model designed for AI alignment research? (2024)
17% chance
Will a single model achieve superhuman performance on all OpenAI gym environments by 2025?
25% chance
Benchmark Gap #5: Once a single AI model solves >= 95% of miniF2F, MATH, and MMLU STEM, will it be less than two years before AI models are used as entry-level data science / data analysis / statistics workers?
67% chance