What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
The Satellite Geo QCM leaderboard, as described in a September 22 DEV Community article by RESK, tests whether a model can select a location from a satellite or aerial image. Each question has four choices; the model’s selected answer is marked right or wrong, with no LLM judge. The published figures are the article’s reported snapshot, not verified live leaderboard values.
What a model is asked to do
Each described item pairs an aerial or satellite image with one question asking the model to choose the correct location from four options. The article says wording and options stay fixed across models, with no hints, retries, or alternate framing. This makes the comparison more controlled for this particular multiple-choice task than an open-ended task whose responses require subjective grading.
The available description does not establish the dataset’s size, image provenance, geographic coverage, train/test or contamination controls, or the exact rubric used to assign difficulty. Those details matter when judging how representative the results are.
Free tools Windows power users keep installed
One-click scans. No signup required.
How answers are scored and displayed
RESK describes scoring as deterministic: a selected option is compared with the answer key and marked right or wrong. There is no LLM judge evaluating free-form text. The article says results are shown as overall accuracy and accuracy by difficulty, alongside a public verbatim response trail where readers can inspect the image, choices, and model answer.
#1 Best Overall
- HOBBY MODEL KIT – Unassembled model packed in an envelope with easy to follow instructions. Ideal for ages 14 and up.
- NO GLUE OR SOLDER NEEDED – Parts can be easily clipped from the metal sheets. Tweezers are the recommended tool for bending and twisting the connection tabs.
- VOYAGER – 1.5 Sheet Model with a moderate difficulty level. Assembled Size: 1.38 x 1.77 x 6.70 inches.
- FROM STEEL SHEETS TO 3D – Pop out the pieces and connect using tabs and holes. Includes illustrated instructions.
- HIGHLY DETAILED ETCHED MODEL – Display your 3D model once completed - collect and build them all.
That trail can help readers examine apparent errors. For example, a wrong answer might reflect difficulty recognizing the location, or a mistake in reading or selecting an option. The article does not present a formal error taxonomy, so those are possible interpretations rather than established categories.
What the reported scores mean
The article’s leaderboard table reports the following accuracy percentages. These are claims from that article’s snapshot, not independently confirmed current rankings.
Rank #2
- Model Kit
- May Require Paints and Glues to Assemble
- Accurate Scale Model
- Detailed Instructions Provided
- Decals/Transfers Included
| Model | Reported accuracy | Context |
|---|---|---|
| DeepSeek V4 Flash Vision (exp) | 98.18% | Reported in RESK’s DEV Community article, posted September 22; the year is not printed on the opened page. |
| GLM 5.2 | 78.0% | Reported in the same table; RESK identifies this as their own submission. |
A score of 98.18% means that the article reports the model selecting the answer key’s correct location on 98.18% of the evaluated questions. It does not mean the model is 98.18% accurate at satellite-image analysis generally, nor does it establish performance on other image types or real-world geospatial work.
Recommended Free Tools
What the leaderboard can—and cannot—establish
Fixed inputs and mechanical scoring make results easier to compare within the described setup. They do not prove that every source of variance or bias has been removed. The material available does not provide enough implementation detail to independently audit dataset construction, geographic balance, submission controls, or whether models may have encountered the items during training.
Rank #3
- HOBBY MODEL KIT – Unassembled model packed in an envelope with easy to follow instructions. Ideal for ages 14 and up
- NO GLUE OR SOLDER NEEDED – Parts can be easily clipped from the metal sheets. Tweezers are the recommended tool for bending and twisting the connection tabs
- APOLLO CSM – 3.5 Sheet Model with a challenging difficulty level. Assembled Size: 5.07 L x 2.28 W x 3.45 H inches.
- FROM STEEL SHEETS TO 3D – Pop out the pieces and connect using tabs and holes. Includes illustrated instructions
- HIGHLY DETAILED ETCHED MODEL – Display your 3D model once completed - collect and build them all
The article itself cautions that the task does not measure reasoning, instruction following, or open-ended vision. Since each item offers four choices, guessing is possible. A headline score is therefore most useful when read alongside the difficulty breakdown and response trail, and when the task resembles the reader’s intended use.
- Compare overall and difficulty-level accuracy: an aggregate can hide weaker performance on harder questions.
- Inspect individual responses: the trail may reveal patterns that a single percentage cannot, though it does not supply a formal error classification.
- Check task fit: success at choosing among four locations is not equivalent to interpreting arbitrary satellite imagery or carrying out geospatial analysis.
- Check the snapshot context: the cited figures are not verified live values, and the retrieved description does not establish the current leaderboard status.
How this differs from another geospatial benchmark
The Cloud-Based Geospatial Benchmark (CBGB) is a separate evaluation and should not be treated as another name for Satellite Geo QCM. A 2025 paper describes CBGB as 45 expert-curated Earth-observation scenarios in which LLM agents generate code to produce short numerical answers. It also compares runs with and without feedback from the execution environment. The paper reports that execution feedback generally helped, that its highest reported performance was 71%, and that reasoning variants outperformed non-thinking variants in that study. These results concern CBGB, not Satellite Geo QCM’s four-option image questions.
Quick Recap
Best Value
- HOBBY MODEL KIT – Unassembled model packed in an envelope with easy to follow instructions. Ideal for ages 14 and up.
- NO GLUE OR SOLDER NEEDED – Parts can be easily clipped from the metal sheets. Tweezers are the recommended tool for bending and twisting the connection tabs.
- HUBBLE TELESCOPE – 1 Sheet Model with a moderate difficulty level. Assembled Size: 3.00 x 2.00 x 2.50 inches.
- FROM STEEL SHEETS TO 3D – Pop out the pieces and connect using tabs and holes. Includes illustrated instructions.
- HIGHLY DETAILED ETCHED MODEL – Display your 3D model once completed - collect and build them all.
Rank #4
- HOBBY MODEL KIT – Unassembled model packed in an envelope with easy to follow instructions. Ideal for ages 14 and up.
- NO GLUE OR SOLDER NEEDED – Parts can be easily clipped from the metal sheets. Tweezers are the recommended tool for bending and twisting the connection tabs.
- JAMES WEBB SPACE TELESCOPE - 2.75 Sheet Model with a moderate difficulty level. Assembled Size: 4.13 L x 2.75 W x 2.75 H inches. 1:221 Scale. 62 Pieces
- FROM STEEL SHEETS TO 3D – Pop out the pieces and connect using tabs and holes. Includes illustrated instructions.
- HIGHLY DETAILED ETCHED MODEL – Display your 3D model once completed - collect and build them all.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Scan for outdated or missing drivers - takes under a minute3Clear out junk files and repair common Windows errors
