AI Paper Atlas

Research map / Benchmarks / AIME24 (Avg@32)

AIME24 (Avg@32) leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AIME24 (Avg@32). Best accuracy: 79.9 (Qwen3-8B + ThreadWeaver, 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 (Avg@32) · accuracy

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

#accuracy ↑MethodPaperTopic
179.9Qwen3-8B + ThreadWeaver
Qwen3-8B
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
ICML 2026 · Table 1
Reasoning and chain of thought
272.19PPPO
Qwen3-8B
Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
AAAI 2026 · Table 1
Reasoning and chain of thought
360.1GR3
DeepSeek-R1-Distill-7B
Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
ICML 2026 · Table 2
RL from feedback
451.8+GPS
DSR-7B
Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
ICML 2026 · Table 2
Reasoning and chain of thought
550DAPO
Qwen2.5-32B
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
NeurIPS 2025 · Main results table
Reasoning and chain of thought
633.4DAPO + EchoRL
Qwen2.5-Math-7B
EchoRL: Reinforcement Learning via Rollout Echoing
ICML 2026 · Table 1
RL from feedback
730.5TBRM n=4
Qwen2.5-Math-7B
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
NeurIPS 2025 · Main Results table
RL from feedback
830DuPO
DeepSeek-R1-Distill-Qwen-1.5B
DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
ICLR 2026 · Table 2
Alignment and preferences
928.65MPOPD
Qwen3-4B-Base
Proposing Better Rollouts for On-Policy Distillation
NeurIPS 2026 · Table 1
Knowledge distillation
1027.5AVSPO
Qwen2.5-14B
Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
ICML 2026 · Table 1
RL from feedback
1 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.