Will Google's Gemini outperform GPT-4 in the SuperGLUE benchmark test by December 2023?
17
closes Dec 31
55%
chance

Google's Gemini, a large-scale machine learning model created by Google DeepMind, was unveiled at Google I/O 2023 [^2^]. The model aims to rival OpenAI's GPT, offering multimodal capabilities never seen in previous models [^3^]. Will Google's Gemini outperform GPT-4 in the SuperGLUE benchmark test by December 2023?

Market Type: YES or NO

Resolution Criteria: This market resolves to YES if Google's Gemini achieves a higher score than GPT-4 in the SuperGLUE benchmark test by December 31, 2023. If not, the market resolves to NO. Official announcements, credible news sources, and/or benchmark results must confirm Gemini's performance.

[^1^]: https://www.zdnet.com/article/every-major-ai-feature-announced-at-google-io-2023/

[^2^]: https://www.theinformation.com/briefings/google-ceo-discloses-gemini-ai-to-rival-openais-gpt

[^3^]: https://blog.google/technology/ai/google-palm-2-ai-large-language-model/

Get Ṁ500 play money

Related questions

[M5000 subsidy] Will finetuned GPT-3.5 solve any freshly-generated Sudoku puzzle? (2023)
Mira avatarMira
47% chance
Will Google Bard become better than GPT-4 at any point before September 2024?
WyattStanke avatarWyatt Stanke
66% chance
Will there be a version of GPT4 with a context window of 100k tokens this year?
SneakySly avatarSneakySly
42% chance
Will mechanistic interpretability be essentially solved for GPT-2 before 2030?
MatthewBarnett avatarMatthew Barnett
30% chance
Will we train GPT-4 to generate resolution criteria better than the creator 50% of the time by the end of 2023?
CrystalBallin avatarCrystal Ballin'
30% chance
Will any Google model exceed chatGPT interest? (by 2025)
Gigacasting avatarGigacasting
54% chance
2) We are going to start running out of data to train large language models.
MattCWilson avatarMatt C. Wilson
24% chance
Will GPT-4 be trained on more than 10T text tokens?
BionicD0LPH1N avatarBionic
23% chance
Will mechanistic interpretability be essentially solved for GPT-3 before 2030?
MatthewBarnett avatarMatthew Barnett
25% chance
Will an open-source LLM beat or match GPT-4 by the end of 2024?
Elon avatarElon
62% chance
Will Gary Marcus tweet at least 10 examples of GPT-4 failure which won't be disproven/fixed within 24 hours? (in 2023)
MrLuke255 avatarMrLuke255
22% chance
Will there be a OpenAI LLM known as GPT-4.5? by 2033
DylanSlagh avatarDylan Slagh
72% chance
There will be an open source LLM approximately as good or better than GPT4 before 2025
NathanpmYoung avatarNathan Young
77% chance
Will a model be trained using at least as much compute as GPT-3 using AMD GPUs before Jan 1 2026?
LeoGao avatarLeo Gao
71% chance
Will GPT, or AI systems that have GPT as their main component, become as reliably factual as Wikipedia, before 2026?
lesaun avatarLesaun
39% chance
Will GPT-5 be released incrementally as GPT4.x for different checkpoints from the training run?
firstuserhere avatarfirstuserhere
37% chance
Will any open-source model achieve GPT-4 level performance on MMLU through 2024?
mattburtell avatarMatt Burtell
64% chance
By 2024, GPTs are proven to be able to infer scientific principles from linguistic data.
Will xAI release an LLM with BIG-Bench score as good as GPT-4 before the end of 2024?
RyanKidd avatarRyan Kidd
58% chance
Will DALL-E 3 be able to generate arbitrary non-adversarial text?
IsaacKing avatarIsaac
17% chance
Sort by:
Benx avatar
Benxbought Ṁ10 of YES

Does the market resolve to NO, if Gemini is not released by December 31? What happens if it's released, but the superGLUE score is not published and can't be tested by us?