SAIL-VL-1.6-8B: benchmark results
Provider: ByteDance. Released 2024-12-01. Access: Open.
Aggregate Rating 1518 ± 19, rank #2087 of 10916 rated models, from 238 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMBench V1.1 CN - Attribute Recognition | 98.9 | Accuracy (%) | 99.8 |
| OpenVLM MMBench V1.1 CN - Image Scene | 93.8 | Accuracy (%) | 99.8 |
| OpenVLM MMBench V1.1 EN - Attribute Recognition | 98.9 | Accuracy (%) | 99.8 |
| OpenVLM AI2D - Parts of the Earth | 92.3 | Accuracy (%) | 99.6 |
| OpenVLM MMBench V1.1 EN - Image Emotion | 85.6 | Accuracy (%) | 99.6 |
| OpenVLM MMBench V1.1 CN - Function Reasoning | 96.7 | Accuracy (%) | 98.9 |
| OpenVLM MMBench V1.1 EN - Image Scene | 92.4 | Accuracy (%) | 98.4 |
| OpenVLM OCRBench - Handwritten Mathematical Expression Recognition | 85 | Correct Answers (%) | 98.4 |
| Open LMM Reasoning - LogicVista - inductive | 43 | Accuracy (%) | 98.1 |
| OpenVLM OCRBench - Scene Text-centric VQA | 95.5 | Correct Answers (%) | 97.5 |
| OpenVLM MMBench V1.1 EN - Action Recognition | 94 | Accuracy (%) | 97.2 |
| OpenVLM MMBench V1.1 CN - Physical Relation | 73.3 | Accuracy (%) | 97 |
Interactive version: theaggregate.ai/model?slug=sail-vl-1-6-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.