AI Paper Atlas

Research map / Benchmarks / MedMCQA

MedMCQA leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MedMCQA. Best accuracy: 78.94 (PRIME, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MedMCQA · accuracy

12 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
178.94PRIME
LLaMA3.3 70B
PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
AAAI 2026 · Table 1
LLM agents
267.32MedS3 Iter 2 w/ PRM
Llama3.1-8B
MedS³: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision
AAAI 2026 · Table 1
Reasoning and chain of thought
366.2PRA
Qwen3-4B-Instruct
Process Reward Agents for Steering Knowledge-Intensive Reasoning
ICML 2026 · Table 1
Retrieval and knowledge
461.4NTK-Selector
Qwen3-8B
Mining Useful General Data for Low-Resource Domain Adaptation
ICML 2026 · Table 1
Instruction and fine-tuning
560.7SENATOR on Qwen2-7B
Qwen2-7B
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
NeurIPS 2025 · Main Results table
Retrieval and knowledge
660.04GoA-Max (3 agents)
7-8B agent pool (6 agents)
Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
ICLR 2026 · Table 1
LLM agents
759.35Skill-MoESkill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills
ICML 2026 · Table 1
Agents, code and math
856.92DKT-large
LLaMA 3-70B
Collaborative Enhancement of Large and Small Models for Question Answering via Dual Knowledge Transfer
AAAI 2026 · Table 2
Visual question answering
954.4Codex + MCP
Codex (Davinci)
Leveraging Large Language Models for Multiple Choice Question Answering
ICLR 2023 · Table 2
Retrieval and knowledge
1052.3CriSPO
Claude Instant
CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation
AAAI 2025 · Table: QA results
Language, safety and interpretability
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.