RSCC
Models describe disaster damage from satellite images taken before and after an event. The authors reserve 988 image pairs from 19 events for testing.
The authors compare ten models under three prompt settings. The ChangePixel team also tested its model on the released subset.
- Made by
- Zhejiang University
- Released
- April 2025
- Kind
- Detection and captioning
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Earth and environmental sciences
- Language
- English
- In and out
- Images, Text, Maps and geodata → Text
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
InternVL3-8B leads with 79.2 among models released by April 2025 InternVL3-8B leads with 79.2 among models released by April 2025
Best score per entry 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. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2025, 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 Astra
- and 16 more
- 1
InternVL3-8B Visual Prompt 79.2
- 2
Pixtral 12B Textual Prompt 79.1
- 3 Qwen2-VL-7B-Instruct Visual Prompt 72.9
- 4 Kimi-VL (3B) Textual Prompt 70.8
- 5 LLaVA-OneVision (8B) Textual Prompt 70.1
- 6 BLIP-3 (3B) Visual Prompt 68.3
- 7 Phi-4-Multimodal (4B) Textual Prompt 67.6
- 8 LLaVA-NeXT-Interleave (8B) Visual Prompt 65.8
- 9 TEOChat (7B) Visual Prompt 62.5
- 10 CCExpert (7B) Textual Prompt 47.1
Source: Official RSCC leaderboard
- 1
InternVL3-8B Visual Prompt 79.2
- 2
Pixtral 12B Textual Prompt 79.1
- 3 Qwen2-VL-7B-Instruct Visual Prompt 72.9
Source: Official RSCC leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 79.2 | Visual Prompt | Apr 2025 | Official leaderboard |
| 2 | | 79.1 | Textual Prompt | Sep 2024 | Official leaderboard |
| 3 | Qwen2-VL-7B-Instruct | 72.9 | Visual Prompt | Aug 2024 | Official leaderboard |
| 4 | Kimi-VL (3B) | 70.8 | Textual Prompt | Official leaderboard | |
| 5 | LLaVA-OneVision (8B) | 70.1 | Textual Prompt | Official leaderboard | |
| 6 | BLIP-3 (3B) | 68.3 | Visual Prompt | Official leaderboard | |
| 7 | Phi-4-Multimodal (4B) | 67.6 | Textual Prompt | Official leaderboard | |
| 8 | LLaVA-NeXT-Interleave (8B) | 65.8 | Visual Prompt | Official leaderboard | |
| 9 | TEOChat (7B) | 62.5 | Visual Prompt | Official leaderboard | |
| 10 | CCExpert (7B) | 47.1 | Textual Prompt | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 79.2 | Visual Prompt | Apr 2025 | Official leaderboard |
| 2 | | 79.1 | Textual Prompt | Sep 2024 | Official leaderboard |
| 3 | Qwen2-VL-7B-Instruct | 72.9 | Visual Prompt | Aug 2024 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official RSCC leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Visual Prompt | 79.2 | ||||
| Textual Prompt | 79.1 | ||||
| Visual Prompt | 78.7 | ||||
| Textual Prompt | 78.6 | ||||
| Qwen2-VL-7B-Instruct | Visual Prompt | 72.9 | |||
| Qwen2-VL-7B-Instruct | Textual Prompt | 72.7 | |||
| Zero-shot | 51.8 | ||||
| Zero-shot | 49.4 | ||||
| Qwen2-VL-7B-Instruct | Zero-shot | 45.5 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official RSCC leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Visual Prompt | 79.2 | ||||
| Textual Prompt | 79.1 | ||||
| Visual Prompt | 78.7 | ||||
| Textual Prompt | 78.6 | ||||
| Qwen2-VL-7B-Instruct | Visual Prompt | 72.9 | |||
| Qwen2-VL-7B-Instruct | Textual Prompt | 72.7 | |||
| Zero-shot | 51.8 | ||||
| Zero-shot | 49.4 | ||||
| Qwen2-VL-7B-Instruct | Zero-shot | 45.5 |
2 models have held number one on the official leaderboard since its release in April 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RSCC 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 RSCC 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for InternVL3-8B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (10 entries).
- Pass Models scored 3 models we track, plus 7 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for InternVL3-8B.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on bili-sakura.github.io: 9 rows for models we track and 7 other entries 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.