AI Paper Atlas

Research map / Benchmarks / SVAMP

SVAMP leaderboard

65 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SVAMP. Best accuracy: 98.16 (SGE, NeurIPS 2024).

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.

SVAMP · accuracy

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

#accuracy ↑MethodPaperTopic
198.16SGE
GPT-4
Self-Guiding Exploration for Combinatorial Problems
NeurIPS 2024 · Reasoning tasks table
Agents, code and math
296.6SafeSieve (ours)
deepseek-V3-671B
SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
AAAI 2026 · Table 1
LLM agents
395.63ARG-Designer
gpt-4o-2024-08-06
Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
AAAI 2026 · Table 2
LLM agents
494.81MAGENavigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
ICML 2026 · Table 1
LLM agents
594.6SSVPO
Qwen3-4B
SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models
ICLR 2026 · Table 1
RL from feedback
694.29rStar
LLaMA3-8B-Instruct
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver
ICLR 2025 · Main results table
Reasoning and chain of thought
794.23LAWA
Qwen3-30B-A3B-Instruct-2507
Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries
NeurIPS 2026 · Table 2
LLM agents
894PRESTO
GPT-4.1
PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
NeurIPS 2025 · Table: Chain-of-Thought Prompt
Language, safety and interpretability
993.7Promptbreeder few-shot
PaLM 2-L
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
ICML 2024 · Table 1
Reasoning and chain of thought
1093.26RADAR
gpt-4o-mini
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
ICML 2026 · Table 1
LLM agents
55 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.