• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    GeoGuess Bench tests AI models on 210 photo-location guesses

    Its creator says Claude Opus 5.5 took first place, scoring higher than Fable 5.1.

    Together AITA
    HassanHA
    2 Sources, ,

    TLDR

    GeoGuess Bench’s creator says each model was asked to locate 210 photos from around the world and scored on how close its guesses came. In the posted results, Claude Opus 5.5 ranked first; Muse Glimmer 30B beat GPT 6 Astra while being about 45 times cheaper; and GLM 5.3 Flash matched GPT 6.1 Sol while being about five times cheaper.

    Combined views

    2.9K

    2 Sources, first seen 2h ago

    Combined views

    2.9K

    2 Sources, first seen 2h ago

    25 likes
    2h ago
    first seen 2h ago
    25 likes
    7 comments
    10 saves
    3 reposts
    7 comments
    10 saves
    3 reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Hassan@nutlopeIntroducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photos from around the world, asked it to predict where each photo was taken, and scored it based on how close it got. Some surprising results: • Muse Glimmer 30B beat GPT 6 Astra while being ~45x cheaper • GLM 5.3 Flash matched GPT 6.1 Sol while being ~5x cheaper • Claude Opus 5.5 took the #1 spot, scoring even higher than Fable 5.1 Open models did surprisingly well overall. Check out the full leaderboard, Pareto frontier curve, and every model's guesses! - Site → http://geoguessbench.com - Code → http://github.com/Nutlope/geoguessbench2h
    Together AI@togethercomputeRT @nutlope: Introducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photo…2h

    2 Sources

    Hassan@nutlopeIntroducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photos from around the world, asked it to predict where each photo was taken, and scored it based on how close it got. Some surprising results: • Muse Glimmer 30B beat GPT 6 Astra while being ~45x cheaper • GLM 5.3 Flash matched GPT 6.1 Sol while being ~5x cheaper • Claude Opus 5.5 took the #1 spot, scoring even higher than Fable 5.1 Open models did surprisingly well overall. Check out the full leaderboard, Pareto frontier curve, and every model's guesses! - Site → http://geoguessbench.com - Code → http://github.com/Nutlope/geoguessbench2h
    Together AI@togethercomputeRT @nutlope: Introducing GeoGuess Bench! A benchmark to measure how good AI models are at playing GeoGuessr. We gave each model 210 photo…2h