Will GPT-5 be capable of achieving superhuman performance in at least one exam that is typically taken by humans?
9
closes 2030
91%
chance

Resolved to YES if there is at least one exam that humans typically take, where GPT-5 or an equivalent flagship model from OpenAI displays superhuman performance. The exact name 'GPT-5' is not necessary.

Edit: To be ‘superhuman’, a GPT-5 or equivalent model has to score higher than the best humans on the same task. If they tie, it only counts if both have a perfect score.

Get Ṁ500 play money

Related questions

(M25000 subsidy!) Will a prompt that enables GPT-4 to solve easy Sudoku puzzles be found? (2023)
Mira avatarMira 🍎
41% chance
GPT-4 with image recognition wins more than half the time against child level opponent?
NathanpmYoung avatarNathan Young
50% chance
Will a prompt that enables GPT-4V (multimodal) to solve easy Sudoku puzzles be found? (2023)
MLGaming avatarMLGaming
50% chance
[M5000 subsidy] Will finetuned GPT-3.5 solve any freshly-generated Sudoku puzzle? (2023)
Mira avatarMira 🍎
33% chance
(M1000 subsidy) Will GPT-4 solve any freshly-generated Sudoku puzzle? (2023)
Mira avatarMira 🍎
70% chance
Will GPT-4 learn to not say that the truck driver driving down a one-way street was walking?
ZviMowshowitz avatarZvi Mowshowitz
70% chance
Will GPT-5 have fewer parameters than GPT-4? (1500M subsidy)
firstuserhere avatarfirstuserhere
24% chance
Can Anyone Make ChatGPT 4 Solve this Middle School Math Problem?
Will GPT-5 be capable of recursive self-improvement?
NathanHelmBurger avatarNathan
25% chance
Will GPT-4 visual model (as released by OpenAI) show ability to tell if an object is inside or outside another object?
firstuserhere avatarfirstuserhere
54% chance
Will GPT-4 be trained (roughly) compute-optimally using the best-known scaling laws at the time?
BionicD0LPH1N avatarBionic
37% chance
Will GPT-5 have over 1 trillion parameters?
Mira avatarMira 🍎
82% chance
Will GPT-4 have over 1 trillion parameters?
EA42 avatarEmbedded Agent
94% chance
Who will find the first prompt enabling GPT-4 to solve one freshly-generated Sudoku puzzle? (multibinary, 2023)
Will an unrestricted GPT-5 be able to make a bioengineered virus?
KabirKumar58cb avatarKabir Kumar
42% chance
Will GPT-4 have 500b+ parameters?
Will GPT-4 be trained on more than 10T text tokens?
BionicD0LPH1N avatarBionic
23% chance
Will there be a version of GPT4 with a context window of 100k tokens this year?
SneakySly avatarSneakySly
42% chance
Will GPT-5 be released incrementally as GPT4.x for different checkpoints from the training run?
firstuserhere avatarfirstuserhere
37% chance
Will GPT-3.5 solve any freshly-generated Sudoku puzzle? (2023)
Mira avatarMira 🍎
21% chance
Sort by:
PrestonJensen avatar
Preston Jensen

What qualifies as superhuman? Depending on your threshold, GPT-4 may already exceed this https://openai.com/research/gpt-4

2 replies
JacobPfau avatar
Jacob Pfau

@PrestonJensen @3684 Standardized tests often report percentiles, so I'd suggest the bar be 'AI must score above the score associated with 99th percentile humans'.

JacobPfau avatar
Jacob Pfau

@JacobPfau (In the absence of more detailed available data). GPT-4 apparently scores near 99th on both GRE Verbal and USABO 2022. However, neither of those meet this bar--the GRE-V being too 'easy' since perfect score is still 99th.