SOTAVerified

Mathematical Reasoning

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 805 papers

TitleStatusHype
HARDMath: A Benchmark Dataset for Challenging Problems in Applied MathematicsCode1
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsCode1
PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularizationCode1
Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form PlanningCode1
Diagram Formalization Enhanced Multi-Modal Geometry Problem SolverCode1
MultiMath: Bridging Visual and Mathematical Reasoning for Large Language ModelsCode1
Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical ReasoningCode1
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight DisentanglementCode1
Toward Adaptive Reasoning in Large Language Models with Thought RollbackCode1
OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization ModelingCode1
LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual ContextsCode1
DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical ReasoningCode1
TheoremLlama: Transforming General-Purpose LLMs into Lean4 ExpertsCode1
Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical ReasoningCode1
H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on TablesCode1
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language FeedbackCode1
Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?Code1
Process-Driven Autoformalization in Lean 4Code1
MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn InteractionsCode1
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code GenerationCode1
STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-MakingCode1
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector BanksCode1
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis ModelsCode1
Embedding Trajectory for Out-of-Distribution Detection in Mathematical ReasoningCode1
VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual ContextCode1
GOLD: Geometry Problem Solver with Natural Language DescriptionCode1
Toward Self-Improvement of LLMs via Imagination, Searching, and CriticizingCode1
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language ModelsCode1
Stepwise Self-Consistent Mathematical Reasoning with Large Language ModelsCode1
ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language ModelsCode1
Learning to Check: Unleashing Potentials for Self-Correction in Large Language ModelsCode1
Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as AgentsCode1
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof DataCode1
Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided InterventionsCode1
Augmenting Math Word Problems via Iterative Question ComposingCode1
Question Translation Training for Better Multilingual ReasoningCode1
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference OptimizationCode1
An In-depth Look at Gemini's Language AbilitiesCode1
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human AnnotationsCode1
Modeling Complex Mathematical Reasoning via Large Language Model based MathAgentCode1
OVM, Outcome-supervised Value Models for Planning in Mathematical ReasoningCode1
Learning From Mistakes Makes LLM Better ReasonerCode1
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and ObservationsCode1
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language ModelsCode1
Ada-Instruct: Adapting Instruction Generators for Complex ReasoningCode1
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-trainingCode1
Auto-Regressive Next-Token Predictors are Universal LearnersCode1
Semi-Supervised Learning via Weight-aware Distillation under Class Distribution MismatchCode1
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module OperationCode1
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and BeyondCode1
Show:102550
← PrevPage 5 of 17Next →
All datasetsAIME24FrontierMathLila (IID)Lila (OOD)PGPS9KAMC23GeoQAMath500UniGeoUniGeo (PRV)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1XolverAcc94.4—Unverified
2DeepSeek-r1Acc79.8—Unverified
3Openai-o1Acc74.4—Unverified
4Openai-o1-miniAcc70—Unverified
5s1-32BAcc56.7—Unverified
6Search-o1Acc56.7—Unverified
7Openai-o1-previewAcc44.6—Unverified
8Qwen2.5-72B-InstructAcc23.3—Unverified
9Claude3.5-SonnetAcc16—Unverified
#ModelMetricClaimedVerifiedStatus
1o3Accuracy0.25—Unverified
2Gemini 1.5 Pro (002)Accuracy0.02—Unverified
3o1-previewAccuracy0.01—Unverified
4GPT-4oAccuracy0.01—Unverified
5Claude 3.5 SonnetAccuracy0.01—Unverified
6o1-miniAccuracy0.01—Unverified
#ModelMetricClaimedVerifiedStatus
1Codex (Few-Shot, 175B)Accuracy0.6—Unverified
2Bhāskara-P (Fine-tuned, 2.7B)Accuracy0.48—Unverified
3Neo-P (Fine-tuned, 2.7B)Accuracy0.39—Unverified
4GPT-3 (Few-Shot, 175B)Accuracy0.38—Unverified
5Bhāskara-A (Fine-tuned, 2.7B)Accuracy0.25—Unverified
6Neo-A (Fine-tuned, 2.7B)Accuracy0.2—Unverified
#ModelMetricClaimedVerifiedStatus
1Codex (Few-Shot, 175B)Accuracy0.59—Unverified
2Bhāskara-P (Fine-tuned, 2.7B)Accuracy0.45—Unverified
3GPT-3 (Few-Shot, 175B)Accuracy0.38—Unverified
4Bhāskara-A (Fine-tuned, 2.7B)Accuracy0.27—Unverified
5Neo-P (Fine-tuned, 2.7B)Accuracy0.24—Unverified
6Neo-A (Fine-tuned, 2.7B)Accuracy0.18—Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDCompletion accuracy65.8—Unverified
2PGPSNetCompletion accuracy62.7—Unverified
3GAPSCompletion accuracy61.2—Unverified
4Inter-GPSCompletion accuracy59.8—Unverified
5GeoformerCompletion accuracy35.6—Unverified
6NGSCompletion accuracy34.1—Unverified
#ModelMetricClaimedVerifiedStatus
1QWQ-32B-previewAcc82.5—Unverified
2Math-MasterAcc82—Unverified
3Qwen2.5-Math-7B-instructAcc62.5—Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDAccuracy (%)75.2—Unverified
2GAPSAccuracy (%)67.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Search-o1Acc86.4—Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDAccuracy (%)98.5—Unverified
#ModelMetricClaimedVerifiedStatus
1GAPSAccuracy (%)97.5—Unverified