SOTAVerified

Arithmetic Reasoning

Papers

Showing 76100 of 175 papers

TitleStatusHype
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsCode1
Learning to Reason for Text Generation from Scientific TablesCode1
LEVER: Learning to Verify Language-to-Code Generation with ExecutionCode1
MathPrompter: Mathematical Reasoning using Large Language ModelsCode1
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human AnnotationsCode1
MoT: Memory-of-Thought Enables ChatGPT to Self-ImproveCode1
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural NetworksCode1
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning ProofsCode1
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLCode1
OpenCQA: Open-ended Question Answering with ChartsCode1
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language ModelsCode1
OVM, Outcome-supervised Value Models for Planning in Mathematical ReasoningCode1
Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic ReasoningCode0
OpenChat: Advancing Open-source Language Models with Mixed-Quality DataCode0
PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuningCode0
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced ReasoningCode0
Self-training Language Models for Arithmetic ReasoningCode0
CodeT5+: Open Code Large Language Models for Code Understanding and GenerationCode0
Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?Code0
Prompt Space Optimizing Few-shot Reasoning Success with Large Language ModelsCode0
Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic SystemsCode0
DiaBlo: Diagonal Blocks Are Sufficient For FinetuningCode0
DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact VerificationCode0
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math QuestionsCode0
SBoRA: Low-Rank Adaptation with Regional Weight UpdatesCode0
Show:102550
← PrevPage 4 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Claude 3.5 Sonnet (HPT)Accuracy97.72Unverified
2DUP prompt upon GPT-4Accuracy97.1Unverified
3Qwen2-Math-72B-Instruct (greedy)Accuracy96.7Unverified
4SFT-Mistral-7B (Metamath, OVM, Smart Ensemble)Accuracy96.4Unverified
5OpenMath2-Llama3.1-70B (majority@256)Accuracy96Unverified
6Jiutian-大模型Accuracy95.2Unverified
7DAMOMath-7B(MetaMath, OVM, BS, Ensemble)Accuracy95.1Unverified
8Claude 3 Opus (0-shot chain-of-thought)Accuracy95Unverified
9OpenMath2-Llama3.1-70BAccuracy94.9Unverified
10GPT-4 (Teaching-Inspired)Accuracy94.8Unverified
#ModelMetricClaimedVerifiedStatus
1Text-davinci-002 (175B)(zero-shot-cot)Accuracy78.7Unverified
2Text-davinci-002 (175B) (zero-shot)Accuracy17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Tree of Thoughts (b=5)Success0.74Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4 (Teaching-Inspired)Accuracy92.2Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4 (Teaching-Inspired)Accuracy89.2Unverified