MM IF-Eval
A challenging multimodal instruction-following benchmark that includes both compose-level constraints for output responses and perception-level constraints tied to input images, with comprehensive evaluation pipeline.
Pixtral-12B from Mistral AI currently leads the MM IF-Eval leaderboard with a score of 0.527 across 1 evaluated AI models.
What MM IF-Eval measures
MM IF-Eval is a multimodal benchmark that evaluates large language models on multimodal, reasoning, and structured output tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.5, with the leader reaching 0.5.
Compare leaders on the best AI for multimodal, best AI for reasoning and best AI for structured output leaderboards.
Publication
- Paper
- MM-IFEngine: Towards Multimodal Instruction Following
- Authors
- Shengyuan Ding, Shenxi Wu, Xiangyu Zhao, Yuhang Zang, and 6 others
- Published
- arXiv
- 2504.07957
Abstract
The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data is scarce, the benchmarks are simple with atomic instructions, and the evaluation strategies are imprecise for tasks demanding exact output constraints. To address this, we present MM-IFEngine, an effective pipeline to generate high-quality image-instruction pairs. Our MM-IFEngine pipeline yields large-scale, diverse, and high-quality training data MM-IFInstruct-23k, which is suitable for Supervised Fine-Tuning (SFT) and extended as MM-IFDPO-23k for Direct Preference Optimization (DPO). We further introduce MM-IFEval, a challenging and diverse multi-modal instruction-following benchmark that includes (1) both compose-level constraints for output responses and perception-level constraints tied to the input images, and (2) a comprehensive evaluation pipeline incorporating both rule-based assessment and judge model. We conduct SFT and DPO experiments and demonstrate that fine-tuning MLLMs on MM-IFInstruct-23k and MM-IFDPO-23k achieves notable gains on various IF benchmarks, such as MM-IFEval (+10.2$\%$), MIA (+7.6$\%$), and IFEval (+12.3$\%$). We have fully open-sourced the datasets (both SFT and DPO), evaluation code and training scripts at https://github.com/SYuan03/MM-IFEngine.
Pixtral-12B leads with 52.7%.
Progress Over Time
Interactive timeline showing model performance evolution on MM IF-Eval
MM IF-Eval Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Mistral AI | 12B | — | — |
FAQ
Common questions about MM IF-Eval.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions