List your company

Autonomous Driving on realistic-highway n10 20-step protocol

0No Collision RateLlama-3.2-3B
-4235077May 21, 2026

Evaluation results

MethodLinks
Llama-3.2-3BMode=Deterministic forecast replay, Model=Llama-3.2-3B2026.0500000-0.81.220.01—
Qwen3-235B-A22BMode=Deterministic forecast replay, Model=Qwen3-235B-A22B2026.059094.581.9243.32.850.180.0130.2
DeepSeek-v4-flashMode=Reactive, Model=DeepSeek-v4-flash2026.0510010081210.520.311.341.37—
Claude Haiku 4.5Mode=Reactive, Model=Claude Haiku 4.52026.05100100723802.051.440.11—
GPT-5.4 miniMode=Reactive, Model=GPT-5.4 mini2026.0510010075.321.510.971.260.03—
Qwen3-235B-A22BMode=Reactive, Model=Qwen3-235B-A22B2026.0510010067.61701.861.370.05—
Llama-3.2-3BMode=Reactive, Model=Llama-3.2-3B2026.051001009.5000.281.190.01—
DeepSeek-v4-flashMode=Deterministic forecast replay, Model=DeepSeek-v4-flash2026.0510010080.916.5017.460.160.138.7
Claude Haiku 4.5Mode=Deterministic forecast replay, Model=Claude Haiku 4.52026.05100100801600.260.180.013.9
GPT-5.4 miniMode=Deterministic forecast replay, Model=GPT-5.4 mini2026.0510010075.8120-1.220.16019.1
Steins;Gate DriveMode=Dual, Model=DeepSeek-v4-flash2026.0510010080.219.5051.161.371.1818.7
Steins;Gate DriveMode=Dual, Model=GPT-5.4 mini2026.0510010074.190.50.41.290.0317
Steins;Gate DriveMode=Dual, Model=Qwen3-235B-A22B2026.0510010072.83905.641.420.0437.8
Steins;Gate DriveMode=Dual, Model=Llama-3.2-3B2026.0510010022.6680-1.031.130.010