Multimodal Reasoning on SEED-Bench (test)
76.22AccuracyLASER-noQ
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LASER-noQModel Backbone=Qwen2-VL 7B, Compression Ratio (rho1)=90%2026.05 | 76.22 | — | |
| LASER-noQModel Backbone=LLaVA-Next 13B, Compression Ratio (rho1)=90%2026.05 | 71.39 | — | |
| LASER-noQModel Backbone=LLaVA-Next 7B, Compression Ratio (rho1)=90%2026.05 | 69.25 | — | |
| LASER-noQModel Backbone=SmolVLM 2B, Compression Ratio (rho1)=90%2026.05 | 68.54 | — | |
| FP16Model Backbone=SmolVLM 2B2026.05 | 68.47 | 76.53 | |
| LASER-noQModel Backbone=SmolVLM 2B, Compression Ratio (rho1)=50%2026.05 | 66.17 | — | |
| LASER-noQModel Backbone=LLaVA-v1.5 7B, Compression Ratio (rho1)=90%2026.05 | 60.14 | — |