AI Paper Atlas

Research map / Benchmarks / AIME 2024

AIME 2024 leaderboard

91 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AIME 2024. Best accuracy: 93.33 (MILES, NeurIPS 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.

AIME 2024 · accuracy

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

#accuracy ↑MethodPaperTopic
193.33MILES
GPT-OSS-20B
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
NeurIPS 2026 · Table 1
Reasoning and chain of thought
293.3CDG
DeepSeek-R1-8B
Inference Time Optimization with Confidence Dynamics
ICML 2026 · Table 1
Reasoning and chain of thought
390PG@16
DeepSeek-R1-Distill-Qwen-32B
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
ICML 2026 · Appendix Table
Reasoning and chain of thought
487.5Seed1.5-Thinking-Enigmata
Seed1.5-Thinking
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
NeurIPS 2025 · Scaling results table
Reasoning and chain of thought
587.1BP-Math-32B BAPO
BP-Math-32B (Qwen2.5-Math SFT)
Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
ICLR 2026 · Table 1
RL from feedback
683.33Soft Thinking w/ Cold Stop
QwQ-32B
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
NeurIPS 2025 · Ablation table
Reasoning and chain of thought
780.1MultiRole-R1
Qwen3-8B
Diversity-Enhanced Reasoning for Subjective Questions
ICLR 2026 · Table AIME
Reasoning and chain of thought
878.1ThoughtFold
Qwen3-8B
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
ICML 2026 · Table 1
Reasoning and chain of thought
975.2ORZ-R1-Distill-Qwen-14B
DeepSeek-R1-Distill-Qwen-14B
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
NeurIPS 2025 · Table: distilled model results
RL from feedback
1073.3Strong-Model Reflective Feedback (F3)
Llama-4-Maverick
FEEDBACK FRICTION: LLMs Struggle to Fully Incorporate External Feedback
NeurIPS 2025 · text
Agents, code and math
40 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

AIME 2024 · pass@1

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

#pass@1 ↑MethodPaperTopic
182.2CAMA
Qwen3-32B
CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge
AAAI 2026 · Table 1
Agents, code and math
281.48Step-entropy pruning (80% low-entropy)
Qwen3-8B
Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
ICLR 2026 · Table 1
Reasoning and chain of thought
379.17SwiReasoning
Qwen3-8B
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
ICLR 2026 · Table 1
Reasoning and chain of thought
478.3RPC (P=4096)
QwQ-32B
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
NeurIPS 2025 · Accuracy table
Reasoning and chain of thought
576.7MathSmith-HC
Qwen3-8B (long-CoT)
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
AAAI 2026 · Table 1
Reasoning and chain of thought
672.5ReTool
DeepSeek-R1-Distill-Qwen-32B
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
ICLR 2026 · Table 1
Reasoning and chain of thought
769.17PM-KVQ 2/4 (BS=12)
DeepSeek-R1-Distill-Qwen-32B
PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
ICLR 2026 · Table 3
Quantization
867.33MixReasoning
Qwen3-8B
MixReasoning: Switching Modes to Think
ICML 2026 · Table 1
Reasoning and chain of thought
964.22SSFT-32B-GFPO
Qwen2.5-32B-Instruct
Training Large Language Models To Reason In Parallel With Global Forking Tokens
ICLR 2026 · Table 1
Reasoning and chain of thought
1061.8G2RPO (lambda=1.5)
DeepSeek-R1-Distill-Qwen-7B
G$^2$RPO: Geometric GRPO; Escaping LLM's Reasoning Rut to Break Accuracy--Entropy Trade-off
ICML 2026 · Table 1
Reasoning and chain of thought
32 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.