Multimodal benchmark # GeoBench leaderboard > GeoBench results for 25 AI models, led by Gemini 3 Flash Preview at 88%. What the benchmark measures, who runs it, and a source for every score. - Canonical page: https://noometry.com/benchmarks/geobench - Last updated: 2026-10-10 - Title: GeoBench Leaderboard (October 2026): Scores by Model As of October 2026, Gemini 3 Flash Preview has the highest published GeoBench score on Noometry at 88%, out of 25 models with results. Last verified October 10, 2026 ## About GeoBench Guessing the country of a street-level photo, in the style of GeoGuessr. - **Category:** [Multimodal](https://noometry.com/best/multimodal) - **Introduced:** 2025 - **Format:** Image to location - **Unit:** Percent (random guessing ≈ 0%) - **Official site:** [geobench.org](https://geobench.org) ## Top 15 models Top models on GeoBench 1. Gemini 3 Flash Preview 88% 2. Gemini 2.5 Pro 86% 3. Gemini 3 Pro 84% 4. GPT-5 81% 5. o1 80% 6. Gemini 2.0 Flash (Feb 2025) 77% 7. Gemini 1.5 Flash (May 2024) 76% 8. Gemini 2.5 Flash 76% 9. Claude Opus 4.5 75% 10. o3 74% 11. GPT-4.1 72% 12. GPT-4o 71% 13. Claude 3.7 Sonnet 68% 14. GPT-4o mini 64% 15. o4-mini 64% 16. 5060708090 Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise) ## All results GeoBench results by model | # | Model | Provider | Score | Setting | Source | Date | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Gemini 3 Flash Preview](https://noometry.com/models/gemini-3-flash-preview) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 88% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 2 | [Gemini 2.5 Pro](https://noometry.com/models/gemini-2-5-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 86% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 3 | [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 84% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 4 | [GPT-5](https://noometry.com/models/gpt-5) | [OpenAI](https://noometry.com/providers/openai) | 81% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 5 | [o1](https://noometry.com/models/o1) | [OpenAI](https://noometry.com/providers/openai) | 80% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 6 | [Gemini 2.0 Flash (Feb 2025)](https://noometry.com/models/gemini-2-0-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 77% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 7 | [Gemini 1.5 Flash (May 2024)](https://noometry.com/models/gemini-1-5-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 76% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 8 | [Gemini 2.5 Flash](https://noometry.com/models/gemini-2-5-flash) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 76% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 9 | [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | [Anthropic](https://noometry.com/providers/anthropic) | 75% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 10 | [o3](https://noometry.com/models/o3) | [OpenAI](https://noometry.com/providers/openai) | 74% | medium | [Epoch AI](https://epoch.ai/benchmarks) | | | 11 | [GPT-4.1](https://noometry.com/models/gpt-4-1) | [OpenAI](https://noometry.com/providers/openai) | 72% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 12 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 71% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 13 | [Claude 3.7 Sonnet](https://noometry.com/models/claude-3-7-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 68% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 14 | [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | [OpenAI](https://noometry.com/providers/openai) | 64% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 15 | [o4-mini](https://noometry.com/models/o4-mini) | [OpenAI](https://noometry.com/providers/openai) | 64% | high | [Epoch AI](https://epoch.ai/benchmarks) | | | 16 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 62% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 17 | [Qwen2.5-VL 72B Instruct](https://noometry.com/models/qwen2-5-vl-72b-instruct) | [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 62% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 18 | [Gemma 3 27B](https://noometry.com/models/gemma-3-27b) | [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 52% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 19 | [Llama 3.2 90B](https://noometry.com/models/llama-3-2-90b) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 52% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 20 | [Llama 4 Maverick](https://noometry.com/models/llama-4-maverick) | [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 52% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 21 | [Claude Opus 4](https://noometry.com/models/claude-opus-4) | [Anthropic](https://noometry.com/providers/anthropic) | 49% | 32K | [Epoch AI](https://epoch.ai/benchmarks) | | | 22 | [Grok 4](https://noometry.com/models/grok-4) | [xAI](https://noometry.com/providers/xai) | 45% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 23 | [Claude Sonnet 4](https://noometry.com/models/claude-sonnet-4) | [Anthropic](https://noometry.com/providers/anthropic) | 37% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 24 | [Pixtral 12B](https://noometry.com/models/pixtral-12b) | [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 37% | | [Epoch AI](https://epoch.ai/benchmarks) | | | 25 | [Claude 3.5 Haiku](https://noometry.com/models/claude-3-5-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 34% | | [Epoch AI](https://epoch.ai/benchmarks) | | ## Compare the leaders - [Gemini 3 Flash Preview vs Gemini 2.5 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-gemini-3-flash-preview) - [Gemini 3 Flash Preview vs Gemini 3 Pro](https://noometry.com/compare/gemini-3-flash-preview-vs-gemini-3-pro) - [Gemini 3 Flash Preview vs GPT-5](https://noometry.com/compare/gemini-3-flash-preview-vs-gpt-5) - [Gemini 3 Flash Preview vs o1](https://noometry.com/compare/gemini-3-flash-preview-vs-o1) - [Gemini 2.5 Pro vs Gemini 3 Pro](https://noometry.com/compare/gemini-2-5-pro-vs-gemini-3-pro) - [Gemini 2.5 Pro vs GPT-5](https://noometry.com/compare/gemini-2-5-pro-vs-gpt-5) ## Other multimodal benchmarks - [LMArena Vision](https://noometry.com/benchmarks/arena-vision) - [Video-MME](https://noometry.com/benchmarks/video-mme) - [VPCT](https://noometry.com/benchmarks/vpct) - [Blueprint-Bench 2](https://noometry.com/benchmarks/blueprint-bench-2) - [Furniture Assembly](https://noometry.com/benchmarks/furniture-assembly) - [LMArena Document](https://noometry.com/benchmarks/arena-document) (reference) - [MindCube](https://noometry.com/benchmarks/mindcube) (reference) - [ScienceQA](https://noometry.com/benchmarks/scienceqa) (reference) - [SpatialViz-Bench](https://noometry.com/benchmarks/spatialviz-bench) (reference) ## Frequently asked questions ### What does GeoBench measure? Guessing the country of a street-level photo, in the style of GeoGuessr. ### Which model has the highest GeoBench score? As of October 2026, Gemini 3 Flash Preview has the highest published GeoBench score on Noometry at 88%, out of 25 models with results. ### What is the best open-weight model on GeoBench? Qwen2.5-VL 72B Instruct has the highest GeoBench accuracy among open-weight models at 62%, ranking 17 of 25 overall. ### Cite this page Noometry. (2026). GeoBench leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/geobench Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/geobench.md).