Research map / Large language models / Agents, code and math
MME-Reasoning: A Broad-Spectrum Benchmark for Evaluating Logical Reasoning in MLLMs
Jiakang Yuan, Tianshuo Peng, Yilei Jiang, Yiting Lu, Renrui Zhang, Kaituo Feng, Chaoyou Fu, Tao Chen, LEI BAI, Bo Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use thinking-mode variant of the model (ablation) | Seed1.5-VL · MME-Reasoning | accuracy (AVG): 47.5 -> 59.9 | Improved |
| train 7B models with rule-based RL (thinking activation) | 7B base MLLMs · MME-Reasoning | accuracy (AVG) | Hurt |
| add MCTS test-time scaling with a 32B reward model (ablation) | Qwen2.5-VL-7B · MME-Reasoning | accuracy (AVG): 26.8 -> 23.3 | Hurt |
| add CoT prompt (ablation) | Qwen2.5-VL-7B · MME-Reasoning | accuracy (AVG): 26.8 -> 24.7 | Hurt |
| add CoT prompt (ablation) | Qwen2.5-VL-32B · MME-Reasoning | accuracy (AVG): 33.2 -> 32.3 | No clear effect |
| add CoT prompt (ablation) | Qwen2.5-VL-72B · MME-Reasoning | accuracy (AVG): 34.1 -> 33.0 | No clear effect |
| add CoT prompt (ablation) | InternVL3-38B · MME-Reasoning | accuracy (AVG): 28.4 -> 32.7 | Improved |
| add CoT prompt (ablation) | InternVL3-78B · MME-Reasoning | accuracy (AVG): 32.1 -> 32.9 | No clear effect |
| add CoT prompt (ablation) | InternVL3-8B · MME-Reasoning | accuracy (AVG): 26.4 -> 25.2 | Hurt |
| longer output (more tokens) across models | MLLMs · MME-Reasoning | accuracy | Mixed |
| replace image with GPT-4o caption and use thinking LLM | DeepSeek-R1 · MME-Reasoning | accuracy (AVG): 46.9 (R1) vs 34.1 (Claude-3.7-Sonnet-Thinking) | Improved |
| increase question difficulty level | models · MME-Reasoning | accuracy | Hurt |
Closest papers by meaning
- MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models (AAAI 2026 · similarity 0.92)
- Think 360deg: Beyond Depth: Evaluating the Width-centric Reasoning Capability of MLLMs (CVPR 2026 · similarity 0.91)
- MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models (AAAI 2026 · similarity 0.90)
- MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency (ICML 2025 · similarity 0.90)
- Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark (ICML 2025 · similarity 0.90)
- MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning (ICLR 2026 · similarity 0.90)
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.
