Released: 2026-04-25
Key:
Score Threshold:
google/gemini-3-flash-preview
Score: 3833
Distance: 532km
Lat: 66.425828
Lng: 18.232345
The landscape features subarctic vegetation including thin-trunked birch trees and low-lying shrubs common in Lapland. The presence of a red and white snow pole is a strong indicator of Northern Sweden. The lighting and foliage suggest a high latitude region, likely within the Norrbotten or Västerbotten counties during late summer or early autumn.
meta-llama/llama-4-maverick
meta
Score: 4198
Distance: 349km
Lat: 60.541928
Lng: 6.556573
The image appears to be a rural or mountainous area with a dirt road, trees, and a body of water in the background. The presence of a red and white pole suggests it might be a trail or path marker. The overcast sky and the type of vegetation are consistent with a Northern European or Scandinavian location. The image’s characteristics, such as the terrain and weather, are typical of Norway. By examining similar Street View images in Norway, I was able to narrow down the location to this specific coordinate.
anthropic/claude-haiku-4.5
anthropic
Score: 3371
Distance: 789km
Lat: 60.5
Lng: 25.8
This image shows a gravel forest road with mixed deciduous and coniferous trees in what appears to be a boreal or temperate climate zone. The vegetation, terrain, and road characteristics are consistent with Nordic regions, particularly Finland or Sweden. The mix of birch and conifer trees, the style of the forest path, and the general landscape composition suggest this is likely in the Scandinavia region. The red and white marker visible on the right side of the road is typical of Finnish forest road markings. The overcast sky and vegetation patterns are consistent with central Finland, around the lakes region.
anthropic/claude-sonnet-4.6
anthropic
Score: 3381
Distance: 782km
Lat: 69.1
Lng: 18.2
The image shows a gravel road through birch trees with a fjord or lake visible in the background. The vegetation, overcast sky, and landscape are characteristic of northern Norway (Troms or Finnmark region). The small birch trees with autumn coloring, the rocky terrain, and the water body visible suggest a location in northern Scandinavia, likely in the Tromsø area of Norway.
x-ai/grok-4-fast
x-ai
Score: 3978
Distance: 457km
Lat: 63.828
Lng: 20.265
The image depicts a gravel road leading to a forested area with birch and coniferous trees showing early autumn colors, adjacent to a calm body of water that appears to be a lake. A small red wooden structure, typical of Scandinavian cabins (stuga in Swedish), is visible in the background. The overcast sky and landscape suggest a rural location in northern Sweden during fall. Coordinates point to a spot near the coast of the Gulf of Bothnia, where such scenery is common, such as around Umeå.
openai/gpt-5-image-mini
openai
Score: 3266
Distance: 852km
Lat: 69.65
Lng: 19.05
Sub‑arctic coastal scene with low mountain birch, fireweed and rocky shoreline — typical of northern Scandinavia. The slim red/white roadside/snow marker pole is characteristic of Norwegian winter markers used along fjord roads. Vegetation and landscape indicate high latitude (around 69°N) on a Norwegian fjord coast, so I placed the guess near Troms/Lyngen area in northern Norway.
moonshotai/kimi-k2.5
moonshot
Score: 4531
Distance: 197km
Lat: 61.508
Lng: 8.575
The image shows several distinctive features that point to Norway: 1) Red and white marker poles (’snøstenger’) are characteristic of Norwegian roads, used to mark road edges during heavy snow; 2) The vegetation consists of birch trees with autumn foliage mixed with conifers, typical of the Norwegian mountain plateau (fjell) at subarctic latitudes; 3) The landscape includes a gravel road alongside a lake with rolling terrain; 4) A small cabin is visible through the trees, consistent with Norwegian mountain cabins (’hytter’). The overcast sky and autumn colors suggest a northern climate. Based on the terrain and vegetation density, this appears to be in the central mountain region of Norway, likely in the Valdres or Jotunheimen area.
Each model receives the same Google Street View image. Models are tasked with guessing the location of the image using only visual clues from the street view. Their answers are evaluated without feedback or retries.