AI Paper Atlas

Research map / Benchmarks / ASDiv

ASDiv leaderboard

18 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ASDiv. Best accuracy: 97.24 (SGE, NeurIPS 2024).

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.

ASDiv · accuracy

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

#accuracy ↑MethodPaperTopic
197.24SGE
GPT-4
Self-Guiding Exploration for Combinatorial Problems
NeurIPS 2024 · Reasoning tasks table
Agents, code and math
296.6SimPO FCS+Reflection
QwQ-32B-Preview
Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
ICML 2025 · Table 4
Reasoning and chain of thought
395.2MoT-2D-Vote (threshold 0.65)
GPT-3.5-turbo / GPT-4
Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
ICLR 2024 · Table (ASDIV)
Reasoning and chain of thought
494.03CoT + Skill-Based
GPT-4-0613
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
NeurIPS 2024 · Transfer of Skill Exemplars to
Agents, code and math
593.46Padé3 (ZFO + AdamW)
Qwen-2.5-Math-1.5B
Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
NeurIPS 2026 · Table 1
Pruning and efficient tuning
692.5DMax
LLaDA-2.0-mini
DMax: Aggressive Parallel Decoding for dLLMs
NeurIPS 2026 · Table 1
Fast diffusion sampling
792.1AdaRS (full)
DeepSeek-R1-Distill-Qwen-1.5B
When Simple Problems Wear Complex Costumes: Improving Efficiency in LRM's Adaptive Reasoning
ICML 2026 · Table 4
Reasoning and chain of thought
884.9Ours-PAL (single chain)
Codex
Self-Evaluation Guided Beam Search for Reasoning
NeurIPS 2023 · Table 1
Reasoning and chain of thought
984.7OpenMath-CodeLlama-70B
CodeLlama-70B
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
NeurIPS 2024 · Table: model comparison
Instruction and fine-tuning
1084.2ToRA-Code-34B
CodeLLaMA-34B
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
ICLR 2024 · Table: Results on 10 mathemati
Agents, code and math
8 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.