AI Paper Atlas

Research map / Benchmarks / NAVSIM v1

NAVSIM v1 leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NAVSIM v1. Best PDMS: 93.5 (DriveSuprim, AAAI 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 · PDMS

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

#PDMS ↑MethodPaperTopic
193.5DriveSuprim
ViT-L
DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
AAAI 2026 · Table 2
Recognition and long-tail
293DriveVLA-W0 (AR expert, best-of-6)DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
ICLR 2026 · Table 1
Robot action and navigation
392.5With perturbed samplesRAP: 3D Rasterization Augmented End-to-End Planning
ICLR 2026 · Table 6
Recognition and long-tail
492.2Ours (SFT+GRPO)
Qwen2.5-0.5B-Instruct
Grounding Driving VLA via Inverse Kinematics
NeurIPS 2026 · Table 1
Human-AI and goal-conditioned
591.3LaST-VLA-8B (RL)
InternVL3-8B
LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
NeurIPS 2026 · Table 1
Robot action and navigation
691.3DriveWorld-VLADriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
ICML 2026 · Table 1
Robot action and navigation
791ELF-VLA-8B
InternVL3-8B
Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
CVPR 2026 · Table 1
Visual and representation RL
890.6AutoDrive-P3 (Ours-Detailed)
Qwen2.5-VL-3B
$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
ICLR 2026 · Table 2
Multimodal LLMs
990.5RFWorld
ResNet-34
Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
NeurIPS 2026 · Table 1
Recognition and long-tail
1090.3WAM-Flow (5 steps)
Janus-1.5B
WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
CVPR 2026 · Table 1
Fast diffusion sampling
2 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.