KRIS-Bench
BAGEL-7B-MoT 60.2 Only in system cards Image editing models follow 1,267 instructions that need factual, conceptual or procedural knowledge across 22 tasks. A GPT-4o judge scores the edits.
The judge rates visual consistency, visual quality, instruction following and knowledge plausibility. NeurIPS 2025 accepted the paper.
In the authors’ words
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing tasks remains under-explored. In this paper, we introduce KRIS-Bench (Knowledge-based Reasoning in Image-editing Systems Benchmark), a diagnostic benchmark designed to assess models through a cognitively informed lens. Drawing from educational theory, KRIS-Bench categorizes editing tasks across three foundational knowledge types: Factual, Conceptual, and Procedural. Based on this taxonomy, we design 22 representative tasks spanning 7 reasoning dimensions and release 1,267 high-quality annotated editing instances. To support fine-grained evaluation, we propose a comprehensive protocol that incorporates a novel Knowledge Plausibility metric, enhanced by knowledge hints and calibrated through human studies. Empirical results on 10 state-of-the-art models reveal significant gaps in reasoning performance, highlighting the need for knowledge-centric benchmarks to advance the development of intelligent image editing systems.
- Level
- School Students, from grade school to high school
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
BAGEL-7B-MoT leads with 60.2
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 BAGEL-7B-MoT 60.2
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | BAGEL-7B-MoT | 60.2 | May 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 20 May 2025 | BAGEL-7B-MoT technical report | 60.2 | KRIS-Bench Overall, BAGEL w/ Self-CoT, evaluated by GPT-4o (Table 10). Without CoT 56.21 | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers. Seed1.5-VL 96.9%