List your company

Waypoint Regression on CosFly-Track (evaluation)

95.6Success Rate @ 1mQwen3.5-9B
22.352841.368960.38579.4011May 18, 2026

Evaluation results

MethodLinks
Qwen3.5-9BParams=9B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0595.61.21395.860.268
GLM-4.6V-FlashParams=4.6B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0595.481.23195.770.274
Qwen3-VL-8BParams=8B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0595.221.24791.880.312
Qwen3.5-2BParams=2B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0595.081.27193.120.298
Qwen3-VL-2BParams=2B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0594.81.31588.450.352
Qwen3.5-0.8BParams=0.8B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0594.51.29887.610.334
Gemma-4-E4BParams=4B, Evaluation Protocol=SFT fine-tuned on CosFly-Track2026.0578.341.52772.330.461
Qwen3-VL-8BParams=8B, Evaluation Protocol=Zero-shot (no fine-tuning)2026.0533.472.60140.781.527
Qwen3.5-0.8BParams=0.8B, Evaluation Protocol=Zero-shot (no fine-tuning)2026.0525.172.87240.411.731
Qwen3.5-2BParams=2B, Evaluation Protocol=Zero-shot (no fine-tuning)2026.0525.172.87240.411.731
Qwen3-VL-2BParams=2B, Evaluation Protocol=Zero-shot (no fine-tuning)2026.0525.172.87240.411.731