Out of them all, Google AI mode outperformed, beating the scores of our last winner ChatGPT o4-mini-high. It also provided better results than Gemini 2.5 Pro Deep Research, despite being powered by a version of Gemini 2.5.
Replies
Google’s AI Mode, was the first, and only model so far, to correctly identify Noordwijk as the location in this photograph, used in both this trial and the one in June. Many models struggled to locate the town with GPT-5 Pro and Thinking wrongly identifying it as a beach in France.
aug 14, 2025, 11:28 am • 94 15 • view
Probably could have killed Bin Laden sooner if we had this capability back then. For years they tried to figure out how to geolocate based on the few pictures they obtained.
aug 14, 2025, 11:36 am • 1 0 • view
I wonder if this success is consistently repetable - LLMs always have a bit of randomness sprinkled.
aug 14, 2025, 12:24 pm • 0 0 • view
See the full results by clicking into our investigation here: www.bellingcat.com/resources/20... If you have a suggestion for what model we should test next or what other OSINT skillsets we should be testing them on, let us know in the comments…
aug 14, 2025, 11:28 am • 38 5 • view
And then there's this lovely map, produced by Chat GPT 5 (see thread):
aug 14, 2025, 1:13 pm • 2 0 • view
Very sobering report, calling for caution in the use of AI - thank you. Could it be that Google has an edge because of its longer history of data collection (and thus advantage in training)?
aug 14, 2025, 11:34 am • 0 0 • view
Google reviews with user loaded photos have been useful for reverse image searches even years prior to all the big money hype about AI.
aug 14, 2025, 12:23 pm • 2 0 • view
📌
aug 14, 2025, 11:30 am • 0 0 • view