GeoGuessBench (Nutlope)
Models place a pin after seeing one street photo. Each game has five rounds, and closer guesses earn more points.
The maker scores 12 models on the same 210 photos from Panoramax and KartaView. The leaderboard reports average points per five-round game.
- Made by
- Nutlope
- Released
- October 2026
- Kind
- Spatial reasoning and counting
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Social and economic geography
- Language
- English
- In and out
- Images → Maps and geodata
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 23412.0 among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 12 more
- 1 Claude Opus 5.5 Medium effort 23412.0
- 2 Claude Fable 5.1 Medium effort 23307.0
- 3
Muse Glimmer Medium effort 22407.0
- 4 GPT-6 Astra Medium effort 21562.0
- 5 GPT-6.1 Sol Medium effort 21194.0
- 6 GLM-5.3-Flash Medium effort 21183.0
- 7 Kimi K3 Medium effort 20431.0
- 8 GPT-6 Luna Medium effort 19560.0
- 9
MiniMax-M3 Medium effort 18451.0
- 10
Qwen3.8 Flash Medium effort 18169.0
- 11
DeepSeek V4.1 Flash Effort 50 of 100 17565.0
- 12
Qwen3.5-9B Medium effort 13441.0
Source: Official GeoGuessBench (Nutlope) leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 23412.0 23005 to 23755 | Medium effort | Sep 2026 | Official leaderboard |
| 2 | Claude Fable 5.1 | 23307.0 22833 to 23723 | Medium effort | Sep 2026 | Official leaderboard |
| 3 | | 22407.0 21884 to 22903 | Medium effort | Aug 2026 | Official leaderboard |
| 4 | GPT-6 Astra | 21562.0 20750 to 22314 | Medium effort | Sep 2026 | Official leaderboard |
| 5 | GPT-6.1 Sol | 21194.0 20342 to 21994 | Medium effort | Sep 2026 | Official leaderboard |
| 6 | GLM-5.3-Flash | 21183.0 20313 to 21985 | Medium effort | Aug 2026 | Official leaderboard |
| 7 | Kimi K3 | 20431.0 19559 to 21260 | Medium effort | Jul 2026 | Official leaderboard |
| 8 | GPT-6 Luna | 19560.0 18635 to 20390 | Medium effort | Sep 2026 | Official leaderboard |
| 9 | | 18451.0 ±987.5 | Medium effort | Jun 2026 | Official leaderboard |
| 10 | | 18169.0 ±959 | Medium effort | Aug 2026 | Official leaderboard |
| 11 | | 17565.0 16528 to 18555 | Effort 50 of 100 | Sep 2026 | Official leaderboard |
| 12 | | 13441.0 ±1245.5 | Medium effort | Feb 2026 | Official leaderboard |
Rankings by part
We read 7 parts from the benchmark’s own leaderboard in 2 groups: location type and region. Each ranks models on one part of the test. Claude Fable 5.1 leads 4 of them, and Claude Opus 5.5 leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.
city
12 models we track have a score here.
- 1 Claude Opus 5.5 24137.0
- 2 Claude Fable 5.1 23903.0
- 3
Muse Glimmer 23200.0
- 4 GPT-6 Astra 22428.0
- 5 GPT-6.1 Sol 22166.0
- 6 Kimi K3 ↑1 21339.0
- 7 GLM-5.3-Flash ↓1 21325.0
- 8 GPT-6 Luna 20458.0
- 9
Qwen3.8 Flash ↑1 18798.0
- 10
MiniMax-M3 ↓1 18782.0
town
12 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 22699.0
- 2 Claude Opus 5.5 ↓1 22673.0
- 3
Muse Glimmer 21599.0
- 4 GLM-5.3-Flash ↑2 21039.0
- 5 GPT-6 Astra ↓1 20679.0
- 6 GPT-6.1 Sol ↓1 20204.0
- 7 Kimi K3 19505.0
- 8 GPT-6 Luna 18645.0
- 9
MiniMax-M3 18114.0
- 10
Qwen3.8 Flash 17528.0
Europe
Mean points per photo, out of 5,000. 12 models we track have a score here.
- 1 Claude Opus 5.5 4680.0
- 2 Claude Fable 5.1 4629.0
- 3
Muse Glimmer 4465.0
- 4 GPT-6 Astra 4387.0
- 5 GPT-6.1 Sol 4372.0
- 6 GLM-5.3-Flash 4261.0
- 7 Kimi K3 4157.0
- 8 GPT-6 Luna 3924.0
- 9
MiniMax-M3 3903.0
- 10
Qwen3.8 Flash 3786.0
Asia
Mean points per photo, out of 5,000. 12 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 4701.0
- 2 Claude Opus 5.5 ↓1 4683.0
- 3
Muse Glimmer 4613.0
- 4 GPT-6 Astra 4548.0
- 5 GLM-5.3-Flash ↑1 4440.0
- 6 GPT-6.1 Sol ↓1 4349.0
- 7 GPT-6 Luna ↑1 4047.0
- 8 Kimi K3 ↓1 4025.0
- 9
Qwen3.8 Flash ↑1 3857.0
- 10
MiniMax-M3 ↓1 3834.0
Americas
Mean points per photo, out of 5,000. 12 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 4769.0
- 2 Claude Opus 5.5 ↓1 4690.0
- 3
Muse Glimmer 4455.0
- 4 GLM-5.3-Flash ↑2 4182.0
- 5 Kimi K3 ↑2 4005.0
- 6 GPT-6 Astra ↓2 3826.0
- 7 GPT-6.1 Sol ↓2 3825.0
- 8 GPT-6 Luna 3498.0
- 9
Qwen3.8 Flash ↑1 2757.0
- 10
DeepSeek V4.1 Flash ↑1 2757.0
Africa
Mean points per photo, out of 5,000. 12 models we track have a score here.
- 1 Claude Fable 5.1 ↑1 4993.0
- 2
Muse Glimmer ↑1 4772.0
- 3 Claude Opus 5.5 ↓2 4694.0
- 4 GPT-6 Luna ↑4 4530.0
- 5 GPT-6 Astra ↓1 4312.0
- 6 GPT-6.1 Sol ↓1 4312.0
- 7 GLM-5.3-Flash ↓1 4201.0
- 8 Kimi K3 ↓1 4158.0
- 9
MiniMax-M3 3943.0
- 10
Qwen3.8 Flash 2806.0
Oceania
Mean points per photo, out of 5,000. 12 models we track have a score here.
- 1 Claude Opus 5.5 4689.0
- 2 Claude Fable 5.1 4371.0
- 3
Muse Glimmer 3892.0
- 4 GPT-6 Luna ↑4 3862.0
- 5
MiniMax-M3 ↑4 3582.0
- 6
Qwen3.8 Flash ↑4 3330.0
- 7 Kimi K3 3325.0
- 8 GPT-6 Astra ↓4 3303.0
- 9 GLM-5.3-Flash ↓3 2847.0
- 10
DeepSeek V4.1 Flash ↑1 2843.0
The best score, 23412.0, costs $0.06 a task
Runs on the cost frontier score higher than any run that's cheaper. Muse Glimmer at Medium effort comes within 1005 of the best for $0.005 a task, 13 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official GeoGuessBench (Nutlope) leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | Medium effort | 23412.0 | $0.06 | 2,015 | |
| Claude Fable 5.1 | Medium effort | 23307.0 | $0.11 | 1,095 | |
| Medium effort | 22407.0 | $0.005 | 2,045 | ||
| GPT-6 Astra | Medium effort | 21562.0 | $0.22 | 3,465 | |
| GPT-6.1 Sol | Medium effort | 21194.0 | $0.04 | 3,210 | |
| GLM-5.3-Flash | Medium effort | 21183.0 | $0.009 | 15,770 | |
| Kimi K3 | Medium effort | 20431.0 | $0.17 | 11,180 | |
| GPT-6 Luna | Medium effort | 19560.0 | $0.004 | 6,065 | |
| Medium effort | 18451.0 | $0.005 | 2,730 | ||
| Medium effort | 18169.0 | $0.003 | 3,925 | ||
| Effort 50 of 100 | 17565.0 | $0.07 | 56,875 | ||
| Medium effort | 13441.0 | $0.01 | 44,970 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official GeoGuessBench (Nutlope) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official GeoGuessBench (Nutlope) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.
Qwen 3.6 Plus 86%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy.
Seed2.1 Pro 90.7%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7%
- MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy.
Qwen 3.8 Max 85.9%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (12 entries).
- Pass Models scored 12 models we track.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on geoguessbench.com: 12 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.