• Cryptomonnaies
  • Marchés de Prédiction
  • Actualités
  • Trading Agentique
  • Articles
  • Ligues

Rechercher des Cryptomonnaies

Cryptomonnaies en tendance



CoinRithm

Entreprise

Entité légale
Bees-x Limited
Numéro de société
13308136
Constituée en
England and Wales
Siège social
Monmouth House, High Street, Watford, England, WD17 1LN

CoinRithm est un service d'information et de recherche exploité par Bees-x Limited. Il n'est pas autorisé par la Financial Conduct Authority (FCA) à exercer des activités réglementées, et rien sur ce site ne constitue un conseil financier.

Explorer

CryptomonnaiesMarchés de PrédictionActualitésArticlesAgent ArenaLigues

Fonctionnalités

Tableau de bordÉchange FictifTrading AgentiquePortefeuilleListe de suiviParamètres

Entreprise

À Propos de NousMethodologieConditions d'utilisationPolitique de ConfidentialitéPolitique en Matière de CookiesAvertissement

Support

Contactez le SupportFAQKit développeurDocs MCP

Réseaux

X (Twitter)FacebookLinkedInTelegramInstagramTikTokYouTube
© 2026 CoinRithm. Tous droits réservés.
Disponible sur Google PlayTélécharger sur l'App Store
  • Accueil
  • MarchésMarchés de Prédiction
  • Actualités
  • Tableau de bord
  1. Marchés de Prédiction
  2. IA
  3. By when will AIs perform at least as well as humans on GAIA?
By when will AIs perform at least as well as humans on GAIA?

By when will AIs perform at least as well as humans on GAIA?

IATechOne-Off9a
Manifold MarketsManifold MarketsSans KYC
Prévision communautaire actuelle
Before 2024-06-01
Before 2024-06-01 0%
En tête parmi 7 options
Prévisionnistes

26

Type de question

multiple choice

Méthodologie

Play-money forecasting platform

Type de source

Prévision

Données du marché

Mis à jour il y a 7 jours

Obsolète
21 févr. 24, 4:362 janv. 36, 7:59

Tendances

Résultat24hProbabilité
Before 2024-06-01
Before 2024-06-01
0%
Before 2025-01-01
Before 2025-01-01
0%

Résultat choisi

Before 2027-01-0192%

Règles

The GAIA benchmark (https://arxiv.org/abs/2311.12983) aims to test for the next level of capability for AI agents.

Manifold Markets
  • Quoting from the paper: "GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency.
  • GAIA questions are conceptually simple for humans yet challenging for most advanced AIs: we show that human respondents obtain 92% vs. 15% for GPT-4 equipped with plugins."
  • This market will resolve based on when an AI system performs as well or better than humans on all 3 of the different levels of the benchmark.
  • I'll use the numbers from Table 4 in paper: 93.9% on level 1, 91.8% on level 2, and 87.3% on level 3.
  • (I'm using the conjunction of all 3 levels rather than the average to be somewhat conservative about this level being achieved.)

Marchés Associés

Which company has best AI model end of July?

Which company has best AI model end of July?

21,1 k €
Anthropic: 82%PolymarketPOLYMARKET
Which company has the best Coding AI model end of June?

Which company has the best Coding AI model end of June?

7,2 k €
Anthropic: 95%PolymarketPOLYMARKET
Will any AI model reach ___ Overall Arena Score by June 30?

Will any AI model reach ___ Overall Arena Score by June 30?

3,7 k €
1510: 28%PolymarketPOLYMARKET
Manifold Markets

GPT 5.6 released by…?

947,9 €
11.59pm ET May 31 2026: 0%Manifold MarketsMANIFOLD MARKETS
Manifold Markets

Will the Technological Singularity occur by January 1st, 2050?

349,5 €
Oui: 50%Manifold MarketsMANIFOLD MARKETS
Manifold Markets

Elon's Tesla promises, Q1 26 Prop Bets

129,9 €
At least 100 Cybercabs produced in 2026: 99%Manifold MarketsMANIFOLD MARKETS

Actifs dans ces sujets

BitcoinBTC$62,632.64+2.54%EthereumETH$1,651.33+2.14%SolanaSOL$65.09+1.78%DogecoinDOGE$0.085+2.01%BNBBNB$594.43+1.80%XRPXRP$1.12+0.55%

Actualités Associées

Anthropic launches Claude Fable 5 with new safeguardsCrypto NewsEU orders Meta to restore WhatsApp access for rival AI chatbotsCrypto NewsJPMorgan plans longer-running AI agents for corporate workflows Crypto NewsOpenAI Files for IPO, Targets Valuation Up to $850BBlockchain.NewsOpenAI confidentially files to go public in the USCointelegraphNvidia expands South Korean AI partnerships across chips, cloud, and robotics Crypto News

Règles

The GAIA benchmark (https://arxiv.org/abs/2311.12983) aims to test for the next level of capability for AI agents.

Manifold Markets
  • Quoting from the paper: "GAIA proposes real-world questions that require a set of fundamental abilities such as reasoning, multi-modality handling, web browsing, and generally tool-use proficiency.
  • GAIA questions are conceptually simple for humans yet challenging for most advanced AIs: we show that human respondents obtain 92% vs. 15% for GPT-4 equipped with plugins."
  • This market will resolve based on when an AI system performs as well or better than humans on all 3 of the different levels of the benchmark.
  • I'll use the numbers from Table 4 in paper: 93.9% on level 1, 91.8% on level 2, and 87.3% on level 3.
  • (I'm using the conjunction of all 3 levels rather than the average to be somewhat conservative about this level being achieved.)