AI Paper Atlas

Research map / Benchmarks / NAVSIM navtest

NAVSIM navtest leaderboard

23 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NAVSIM navtest. Best PDMS: 92.4 (NoRD-BoN, CVPR 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.

NAVSIM navtest · PDMS

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

#PDMS ↑MethodPaperTopic
192.4NoRD-BoN
Qwen2.5-VL-3B-Instruct
NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
CVPR 2026 · Table 3
Multimodal LLMs
292GaussianFusion
V2-99
GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving
NeurIPS 2025 · Table 1
3D generation
391.6SafeDriveSafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
CVPR 2026 · Table 1
Recognition and long-tail
491.5Driving with Advice
Qwen2.5-VL-3B + diffusion planner
Driving with Advice: Large Model as Motion Advisor for Joint Planning
AAAI 2026 · Table 1
Robot action and navigation
591.4ASSCG (RecogDrive-based dual system)
ReCogDrive
ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving
ECCV 2026 · Table 2
Recognition and long-tail
691ReflectDrive-2ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
NeurIPS 2026 · Table 4
Offline RL
790.8ReCogDrive
InternVL3-8B, camera only
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
ICLR 2026 · Table 1
Robot action and navigation
890.7SeerDrive†
V2-99
Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
NeurIPS 2025 · Table 1
Molecules and proteins
990.4DriveTeach-VLA
Qwen2.5-VL-3B
Teaching Vision-Language-Action Models What to See and Where to Look
ECCV 2026 · Table 1
Robot action and navigation
1090.2VeteranAD
ResNet-34 (camera)
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
AAAI 2026 · Table 1
Recognition and long-tail
13 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.