Will an AI system beat humans in the GAIA benchmark before the end of 2025?
11
Ṁ110Ṁ587resolved Apr 20
Resolved
NO1H
6H
1D
1W
1M
ALL
GAIA: a benchmark for General AI Assistants
paper: https://arxiv.org/abs/2311.12983
GPT4 scored only 15% compared to 92% for humans
I will resolve based on open source results or official reputable company announcements/papers.
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ43 | |
| 2 | Ṁ20 | |
| 3 | Ṁ18 | |
| 4 | Ṁ16 | |
| 5 | Ṁ6 |
Sort by:
Good market. A good resolution source might be the average score on the test set https://huggingface.co/spaces/gaia-benchmark/leaderboard
I would be interested in a market that ends at the end of 2029.
People are also trading
Related questions
By when will AIs perform at least as well as humans on GAIA?
Will AIs beat human experts in question-answering on the GPQA benchmark before January 1st, 2027?
95% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?
39% chance
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
67% chance
Will any AI achieve a score of 25% on ARC-AGI-3 by the end of 2026?
40% chance
Will AI beat top Magic the Gathering human player before the end of 2026?
5% chance
Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?
80% chance
Will an AI system similar to Auto-GPT make a successful attempt to kill a human by 2030?
27% chance
Will AI wipe out AI before the year 2030?
4% chance
Will AI beat top Magic the Gathering human player before the end of 2028?
29% chance