AI Paper Atlas

Research map / Benchmarks / MAWPS

MAWPS leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MAWPS. Best accuracy: 95.7 (OpenMath-CodeLlama-70B, 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.

MAWPS · accuracy

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

#accuracy ↑MethodPaperTopic
195.7OpenMath-CodeLlama-70B
CodeLlama-70B
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
NeurIPS 2024 · Table: model comparison
Instruction and fine-tuning
293.6Q-Function PPO
Codellama Base
Learning Goal-Conditioned Representations for Language Reward Models
NeurIPS 2024 · Table: Policy model performanc
RL from feedback
393.3ToRA-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
493.3Chain of thought
PaLM 540B
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
NeurIPS 2022 · Table
Reasoning and chain of thought
592.67CoRe
GPT-3.5-turbo
Can LLMs Solve Longer Math Word Problems Better?
ICLR 2025 · Generalization table
Agents, code and math
683.1DPO-BMC
Llama2-7B-base
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
ICLR 2025 · Table 1
Alignment and preferences
781.4SocraticLM
ChatGLM3-6b
SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
NeurIPS 2024 · Table 2
Agents, code and math
880.67MoDr
Huginn-3.5B
MoDr: Mixture-of-Depth-Recurrent Transformers for Test-Time Reasoning
ICLR 2026 · Figure 3
Reasoning and chain of thought
980.3HMSHMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word Problem
AAAI 2021 · Table 2
Agents, code and math
1074D-LLM
LLaMA2-7B
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
NeurIPS 2024 · Table 1
Reasoning and chain of thought
4 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.