AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

GradingBench: Evaluating End-to-End Compositional Reasoning of MLLMs for Automated Exam Grading

Yuting Wang, Zixian Guo, Weihao You, Zhilong Ji, Jinfeng Bai, Wangmeng Zuo

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
provide reference answers (answer-based instead of answer-free) (ablation)Gemini-3.1-Pro · GradingBench L1accuracy: 79.60 -> 89.74Improved
provide reference answers (ablation)Gemini-3.1-Pro · GradingBench L3accuracy: 70.06 -> 81.78Improved
give gold bounding box coordinates of the target question (L2) versus autonomous full page (L3) (ablation)Doubao-seed-2.0-Pro · GradingBench answer-freeaccuracy: 68.14 -> 46.30Hurt
decompose L3 grading into 3 rounds (perception, reasoning, grading) (ablation)Gemini-2.5-Pro · GradingBench L3 answer-freeaccuracy: 50.94 -> 58.40Improved
decompose L3 grading into 3 rounds (ablation)Qwen3-VL-235B-A22B · GradingBench L3 answer-freeaccuracy: 47.42 -> 58.48Improved
decompose L3 grading into 3 rounds (ablation)Gemini-3.1-Pro · GradingBench L3 answer-freeaccuracy: 70.06 -> 74.38Improved
decompose L3 grading into 3 rounds (ablation)Qwen2.5-VL-72B · GradingBench L3 answer-freeaccuracy: 23.33 -> 19.44Hurt
run localization in isolation instead of within the integrated L1 prompt (ablation)Gemini-2.5-Pro · GradingBench L1mAP: 29.34 -> 40.74Improved
supervised fine-tune Qwen2.5-VL-7B on ~10K grading examplesQwen2.5-VL-7B · GradingBench L3 answer-freeaccuracy: 8.38 -> 52.65Improved
supervised fine-tune Qwen2.5-VL-7BQwen2.5-VL-7B · GradingBench L1mAP: 0.93 -> 84.81Improved
supervised fine-tune Qwen2.5-VL-7B (reasoning accuracy still behind Gemini-3.1-Pro)Qwen2.5-VL-7B · GradingBench average answer-freeaverage: 8.20 -> 57.47 vs Gemini 61.27Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy