AI Paper Atlas

Research map / Benchmarks / NAVSIM v1 navtest

NAVSIM v1 navtest leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NAVSIM v1 navtest. Best PDMS: 95.1 (DrivoR (+SimScale) + Ours, ECCV 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 v1 navtest · PDMS

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

#PDMS ↑MethodPaperTopic
195.1DrivoR (+SimScale) + Ours
DrivoR
Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving
ECCV 2026 · Table 2
Recognition and long-tail
294.8ChainFlow-VLA (trainval)ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
NeurIPS 2026 · Table 1
Robot action and navigation
393.8RAP-DINO
DINOv3-H+
RAP: 3D Rasterization Augmented End-to-End Planning
ICLR 2026 · Table 1
Recognition and long-tail
493.7DrivoR
DINOv2 ViT-S
Driving on Registers
CVPR 2026 · Table 1
Attention and transformers
593.7ExploreVLA (best-of-N)ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
ECCV 2026 · Table 1
Robot action and navigation
692.1HybridDriveVLAFrom Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
NeurIPS 2026 · Table 3
Robot action and navigation
792SparseDriveV2
ResNet-34
SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
ECCV 2026 · Table 2
Recognition and long-tail
891.8DriveFine* (score-based RFT)DriveFine: Refining-Augmented Masked Diffusion VLA for Accurate and Robust Driving
ECCV 2026 · Table 1
Robot action and navigation
991.4CoPhyDistill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
NeurIPS 2026 · Table 1
Visual and representation RL
1091.3IRR-Drive-4B
Qwen3-VL-4B
Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving
NeurIPS 2026 · Table 1
Robot action and navigation
6 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.