AI Paper Atlas

Research map / Benchmarks / AIME24

AIME24 leaderboard

127 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AIME24. Best accuracy: 97.3 (HyPER, ICML 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.

AIME24 · accuracy

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

#accuracy ↑MethodPaperTopic
197.3HyPER
Qwen3-Next-80B-A3B-Thinking
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
ICML 2026 · Table 1
Reasoning and chain of thought
293.3Think@n
OSS-120B-medium
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
ICML 2026 · Table 2
Reasoning and chain of thought
390QwQ-32B BoN w/ Self-PRM @32
QwQ-32B
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
NeurIPS 2025 · Table 4
Reasoning and chain of thought
489ToCoRL
Qwen3-30B-A3B-2507-Thinking
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
ICML 2026 · Table 2
Reasoning and chain of thought
586.7RICE {(70,47), (23,115)}
Qwen3-235B
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
NeurIPS 2025 · Table 3
Reasoning and chain of thought
686.67RTPurbo w/ top-p
Qwen3-30B-A3B-Think
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
NeurIPS 2026 · Table 3
Attention and transformers
783.3Ours
Controller Qwen2.5-7B-Base (System 1: Qwen3-30B-A3B, Qwen2.5
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
NeurIPS 2026 · Table 1
LLM agents
881.8Seirênes
Qwen3-30B-A3B
Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
NeurIPS 2026 · Table 1
Reasoning and chain of thought
981.5OEA k0=5
Qwen3-30B-A3B
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
ICML 2026 · Table 1
Mixture of experts
1080MAD-M2 (objective masking)
QwQ-32B
Multi-Agent Debate with Memory Masking
ICLR 2026 · Table 1
LLM agents
75 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

AIME24 · pass@1

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

#pass@1 ↑MethodPaperTopic
186.7DyCon (Ours)
Qwen3-4B-Thinking-2507
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
ICML 2026 · Table 1
Reasoning and chain of thought
285.2MetaStone-S1-32B-high
QwQ-32B
Test-Time Scaling with Reflective Generative Model
ICLR 2026 · Table 1
Reasoning and chain of thought
383PADD
Qwen3-30B-A3B student
PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
ICML 2026 · Table 1
Reasoning and chain of thought
477.8Adaptive control
QwQ-32B
Controlling Thinking Speed in Reasoning Models
NeurIPS 2025 · Adaptive control results table
Reasoning and chain of thought
576.5CoNL
Qwen3-8B
Conversation for Non-verifiable Learning: Self-Evolving Large Language Models through Meta-Evaluation
ICML 2026 · Table 3
Agents, code and math
676.2CRAFT
Qwen3-4B-Thinking
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
ICML 2026 · Table 2
Reasoning and chain of thought
774.1Evolve@240
Qwen3-8B (Thinking)
Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
ICML 2026 · Table 2
Agents, code and math
873.3ReBalance
Qwen3-14B
Efficient Reasoning with Balanced Thinking
ICLR 2026 · Table 1
Reasoning and chain of thought
973.1HICRA
Qwen3-4B-Instruct-2507
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
ICLR 2026 · Table 1
Reasoning and chain of thought
1070ProRL + GooseReason-0.7M (+270 steps)
Qwen3-4B-Instruct
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
ICML 2026 · Table 1
Reasoning and chain of thought
34 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.