SOTAVerified

Mathematical Reasoning

Papers

Showing 751800 of 805 papers

TitleStatusHype
Peano: Learning Formal Mathematical ReasoningCode1
PAL: Program-aided Language ModelsCode3
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic AbstractionsCode0
Galactica: A Large Language Model for ScienceCode4
Overcoming Barriers to Skill Injection in Language Modeling: Case Study in ArithmeticCode0
Blank Collapse: Compressing CTC emission for the faster decodingCode0
Lila: A Unified Benchmark for Mathematical ReasoningCode1
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language ModelsCode1
Multi-View Reasoning: Consistent Contrastive Learning for Math Word ProblemCode2
Composing Ensembles of Pre-trained Models via Iterative Consensus0
Learning to Reason With Relational Abstractions0
Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-ThoughtCode3
Weakly Supervised Formula Learner for Solving Mathematical ProblemsCode0
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical ReasoningCode1
CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical ReasoningCode1
Transformers discover an elementary calculation system exploiting local attention and grid-like problem representationCode0
MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems0
Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solvers0
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks0
Training Compute-Optimal Large Language ModelsCode6
Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library0
Why are NLP Models Fumbling at Elementary Math? A Survey of Automatic Word Problem Solvers0
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human LevelCode1
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
Theoretical Analysis of an XGBoost Framework for Product Cannibalization0
GraphMR: Graph Neural Network for Mathematical Reasoning0
Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems0
Training Verifiers to Solve Math Word ProblemsCode3
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language ReasoningCode1
Conjectures, Tests and Proofs: An Overview of Theory Exploration0
A Reinforcement Learning Environment for Mathematical Reasoning via Program SynthesisCode1
Reasoning with Transformer-based Models: Deep Learning, but Shallow ReasoningCode0
LoRA: Low-Rank Adaptation of Large Language ModelsCode2
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical ReasoningCode1
Compositional Processing Emerges in Neural Networks Solving Math ProblemsCode0
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic ReasoningCode1
Sustainability of Collusion and Market Transparency in a Sequential Search Market: a Generalization0
The Role of General Intelligence in Mathematical Reasoning0
Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units0
Measuring Mathematical Problem Solving With the MATH DatasetCode2
LIME: Learning Inductive Bias for Primitives of Mathematical ReasoningCode1
SMART: A Situation Model for Algebra Story Problems via Attributed Grammar0
Noisy Deductive Reasoning: How Humans Construct Math, and How Math Constructs Universes0
Reverse Operation based Data Augmentation for Solving Math Word ProblemsCode0
DRLE: Decentralized Reinforcement Learning at the Edge for Traffic Light Control in the IoVCode2
Adventures in Mathematical Reasoning0
IsarStep: a Benchmark for High-level Mathematical ReasoningCode1
Mathematical Reasoning via Self-supervised Skip-tree Training0
Compositional Generalization with Tree Stack Memory UnitsCode0
Mathematical Reasoning in Latent Space0
Show:102550
← PrevPage 16 of 17Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1XolverAcc94.4Unverified
2DeepSeek-r1Acc79.8Unverified
3Openai-o1Acc74.4Unverified
4Openai-o1-miniAcc70Unverified
5Search-o1Acc56.7Unverified
6s1-32BAcc56.7Unverified
7Openai-o1-previewAcc44.6Unverified
8Qwen2.5-72B-InstructAcc23.3Unverified
9Claude3.5-SonnetAcc16Unverified
#ModelMetricClaimedVerifiedStatus
1o3Accuracy0.25Unverified
2Gemini 1.5 Pro (002)Accuracy0.02Unverified
3GPT-4oAccuracy0.01Unverified
4o1-miniAccuracy0.01Unverified
5o1-previewAccuracy0.01Unverified
6Claude 3.5 SonnetAccuracy0.01Unverified
#ModelMetricClaimedVerifiedStatus
1Codex (Few-Shot, 175B)Accuracy0.6Unverified
2Bhāskara-P (Fine-tuned, 2.7B)Accuracy0.48Unverified
3Neo-P (Fine-tuned, 2.7B)Accuracy0.39Unverified
4GPT-3 (Few-Shot, 175B)Accuracy0.38Unverified
5Bhāskara-A (Fine-tuned, 2.7B)Accuracy0.25Unverified
6Neo-A (Fine-tuned, 2.7B)Accuracy0.2Unverified
#ModelMetricClaimedVerifiedStatus
1Codex (Few-Shot, 175B)Accuracy0.59Unverified
2Bhāskara-P (Fine-tuned, 2.7B)Accuracy0.45Unverified
3GPT-3 (Few-Shot, 175B)Accuracy0.38Unverified
4Bhāskara-A (Fine-tuned, 2.7B)Accuracy0.27Unverified
5Neo-P (Fine-tuned, 2.7B)Accuracy0.24Unverified
6Neo-A (Fine-tuned, 2.7B)Accuracy0.18Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDCompletion accuracy65.8Unverified
2PGPSNetCompletion accuracy62.7Unverified
3GAPSCompletion accuracy61.2Unverified
4Inter-GPSCompletion accuracy59.8Unverified
5GeoformerCompletion accuracy35.6Unverified
6NGSCompletion accuracy34.1Unverified
#ModelMetricClaimedVerifiedStatus
1QWQ-32B-previewAcc82.5Unverified
2Math-MasterAcc82Unverified
3Qwen2.5-Math-7B-instructAcc62.5Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDAccuracy (%)75.2Unverified
2GAPSAccuracy (%)67.8Unverified
#ModelMetricClaimedVerifiedStatus
1Search-o1Acc86.4Unverified
#ModelMetricClaimedVerifiedStatus
1GOLDAccuracy (%)98.5Unverified
#ModelMetricClaimedVerifiedStatus
1GAPSAccuracy (%)97.5Unverified