AI Paper Atlas

Research map / Benchmarks / StrategyQA

StrategyQA leaderboard

46 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on StrategyQA. Best accuracy: 96.3 (TG-RAG, ICML 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.

StrategyQA · accuracy

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

#accuracy ↑MethodPaperTopic
196.3TG-RAG
Qwen3-32B
TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
ICML 2026 · Table 1
Retrieval and knowledge
292.6ORACLE
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
391.3ReGenesis (Self-Consistency)
Mistral-7B-Instruct-v0.3
ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
ICLR 2025 · In-domain results table
Reasoning and chain of thought
490.4Satori-Qwen-7B (Round 2)
Qwen-2.5-Math-7B
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
ICML 2025 · Table: Results on Out-of-domai
Reasoning and chain of thought
585.96LASeR
Llama-3-8B
LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
NeurIPS 2025 · Main Results reasoning table
Reasoning and chain of thought
685.7PGTS (SC8)
LLaMA3.1-8B
Policy Guided Tree Search for Enhanced LLM Reasoning
ICML 2025 · Table 1
Reasoning and chain of thought
784AoT
GPT-4
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
ICML 2024 · Table: question-answer tasks
Reasoning and chain of thought
883.49SGE
GPT-4
Self-Guiding Exploration for Combinatorial Problems
NeurIPS 2024 · Reasoning tasks table
Agents, code and math
981.7ESC
GPT-4
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
ICLR 2024 · Table 1
Reasoning and chain of thought
1081.6Self-consistency
PaLM-540B
Self-Consistency Improves Chain of Thought Reasoning in Language Models
ICLR 2023 · Table 2
Reasoning and chain of thought
36 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.