AI Paper Atlas

Research map / Benchmarks / ProofWriter

ProofWriter leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ProofWriter. Best accuracy: 97 (+LogicReward, ICLR 2026).

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.

ProofWriter · accuracy

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

#accuracy ↑MethodPaperTopic
197+LogicReward
Qwen3-8B
LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
ICLR 2026 · Table 1
Reasoning and chain of thought
296.7CLOVER
gpt-4o
Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
ICLR 2025 · Table 1
Agents, code and math
394.18o3-mini SMT
o3-mini
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
NeurIPS 2025 · Benchmarking accuracy table
Agents, code and math
492.32HBLR
DeepSeek-R1
From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
AAAI 2026 · Table 3
Agents, code and math
592Ours (w/ sparse)
GPT-4
Enhancing Complex Symbolic Logical Rea­soning of Large Language Models via Sparse Multi-Agent Debate
ICLR 2026 · Table 1
LLM agents
679.6SIPDO
GPT-4o
SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
ICLR 2026 · Table 3
Language, safety and interpretability
771.8MoT training, MoT inference
Qwen2.5-7B-Instruct
Learning to Reason via Mixture-of-Thought for Logical Reasoning
ICLR 2026 · Table 1
Reasoning and chain of thought
868.2ORACLE
Qwen-2.5-7B-Instruct
ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
AAAI 2026 · Table 1
Reasoning and chain of thought
965.67Llama3.1-8B-Instruct finetuned on ProverQA
Llama3.1-8B-Instruct
Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
ICLR 2025 · Finetuning Evaluation Results
Reasoning and chain of thought
1064.8SoT
Llama-3.1-8B
State of Thought Enables Endogenous Reasoning
NeurIPS 2026 · Table 1
Reasoning and chain of thought

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.