ReasonSeg
Models infer which object an instruction describes and return its mask. Instructions can require reasoning about the image.
- Made by
- ReasonSeg team
- Released
- August 2023
- Kind
- Detection and captioning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Image, video and 3D generation
LISA-13B-LLaVA1.5 tops the leaderboard with 61.3% No scores yet
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as OVSeg (LLaVA-v1.5-13B + OVSeg), are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
- 1 LISA-13B-LLaVA1.5 Fine-tuned on 239 ReasonSeg examples 61.3%
- 2 LISA-7B-LLaVA1.5 Fine-tuned on 239 ReasonSeg examples 55.6%
- 3 LISA-13B Fine-tuned on 239 ReasonSeg examples 51.7%
- 4 LISA-7B Fine-tuned on 239 ReasonSeg examples 47.3%
- 5 OVSeg (LLaVA-v1.5-13B + OVSeg) 41.5%
- 6 LLaVA1.5-7B + OVSeg 39.7%
- 7 OVSeg 26.1%
- 8 SEEM 24.3%
- 9 X-Decoder 21.7%
- 10 GRES 21.3%
- 11 Grounded-SAM 21.3%
Source: The ReasonSeg paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LISA-13B-LLaVA1.5 | 61.3% | Fine-tuned on 239 ReasonSeg examples | Official leaderboard | |
| 2 | LISA-7B-LLaVA1.5 | 55.6% | Fine-tuned on 239 ReasonSeg examples | Official leaderboard | |
| 3 | LISA-13B | 51.7% | Fine-tuned on 239 ReasonSeg examples | Official leaderboard | |
| 4 | LISA-7B | 47.3% | Fine-tuned on 239 ReasonSeg examples | Official leaderboard | |
| 5 | OVSeg (LLaVA-v1.5-13B + OVSeg) | 41.5% | Oct 2023 | Official leaderboard | |
| 6 | LLaVA1.5-7B + OVSeg | 39.7% | OVSeg | Official leaderboard | |
| 7 | OVSeg | 26.1% | Official leaderboard | ||
| 8 | SEEM | 24.3% | Official leaderboard | ||
| 9 | X-Decoder | 21.7% | Official leaderboard | ||
| 10 | GRES | 21.3% | Official leaderboard | ||
| 11 | Grounded-SAM | 21.3% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|
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 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (11 entries).
- Pass Models scored 11 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 1 row for models we track and 10 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.