BailingMM-Lite-1203: benchmark results
Provider: InclusionAI. Released 2024-12-03. Access: API.
Aggregate Rating 1519 ± 39, rank #2071 of 10916 rated models, from 433 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM AI2D - Food Chains and Webs | 99.1 | Accuracy (%) | 100 |
| OpenVLM MMT-Bench - Rotated Object Detection | 88.9 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Scene Text Recognition | 100 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Social Relation Recognition | 80 | Score (%) | 99.3 |
| OpenVLM MathVista - VQA | 67.6 | Accuracy (%) | 99.1 |
| OpenVLM MMT-Bench - Handwritten Mathematical Expression Recognition | 100 | Score (%) | 97.8 |
| OpenVLM MMT-Bench - Scene Recognition | 85 | Score (%) | 97.3 |
| OpenVLM MMBench V1.1 CN - Image Quality | 68.5 | Accuracy (%) | 97.2 |
| OpenVLM MMT-Bench - Helmet Anomaly Detection | 95 | Score (%) | 97.1 |
| OpenVLM MathVista - NUM | 59 | Accuracy (%) | 96.9 |
| OpenVLM HallusionBench - aAcc | 75 | Accuracy (%) | 96.8 |
| OpenVLM MMT-Bench - Abstract Visual Recognition | 90 | Score (%) | 96.8 |
Interactive version: theaggregate.ai/model?slug=bailingmm-lite-1203 · How It Works · Data refreshed daily, snapshot 2026-11-08.