AI Paper Atlas

Research map / Benchmarks / MMLU 5-shot

MMLU 5-shot leaderboard

27 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MMLU 5-shot. Best accuracy: 84.7 (DRAFT-RL, 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.

MMLU 5-shot · accuracy

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

#accuracy ↑MethodPaperTopic
184.7DRAFT-RL
Claude-3.5-Sonnet
DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs
AAAI 2026 · Table 3
LLM agents
281.79MicroMix
Qwen2.5-32B
MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models
ICLR 2026 · Table 1
Quantization
375.2Flan-PaLM 540B CoT + self-consistency
PaLM-540B
Scaling Instruction-Finetuned Language Models
JMLR 2024 · Table 4
Language, safety and interpretability
472.2Llama 3.1 405B LoLCATs
Llama 3.1 405B
LoLCATs: On Low-Rank Linearizing of Large Language Models
ICLR 2025 · Table 5
Reasoning and chain of thought
571.77Bohdi
Gemma2-9B-IT
Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
NeurIPS 2025 · Table 1
Agents, code and math
671.7Proposed
Mixtral-8x7B
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
ICML 2025 · Quality of Generated Output ta
Mixture of experts
769.4NOLA
LLaMA-2 70B (8-bit)
NOLA: Compressing LoRA using Linear Combination of Random Basis
ICLR 2024 · Instruction finetuning table
Pruning and efficient tuning
866.62APE full
Four base models (average)
APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
ICLR 2025 · APE component ablation table
Attention and transformers
963.8Minitron 8B
Nemotron-4 15B
Compact Language Models via Pruning and Knowledge Distillation
NeurIPS 2024 · Table: 8B community model comp
Reasoning and chain of thought
1063.7REBEL
OpenChat-3.5
REBEL: Reinforcement Learning via Regressing Relative Rewards
NeurIPS 2024 · General Chat Results table
RL from feedback
17 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.