Step-1.5V-mini: benchmark results
Provider: StepFun. Released 2024-07-04. Access: API.
Aggregate Rating 1476 ± 34, rank #2722 of 10916 rated models, from 433 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - IEJ | 70 | Score (%) | 99.5 |
| OpenVLM MMBench V1.1 EN - Identity Reasoning | 100 | Accuracy (%) | 99.1 |
| OpenVLM MMT-Bench - Single Object Tracking | 80 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Image Quality Assessment | 75 | Score (%) | 98.5 |
| OpenVLM MMBench V1.1 CN - Identity Reasoning | 100 | Accuracy (%) | 97.9 |
| OpenVLM MMBench V1.1 EN - Image Style | 88 | Accuracy (%) | 97.9 |
| OpenVLM MMT-Bench - Counting By Category | 46.2 | Score (%) | 97.8 |
| OpenVLM MMT-Bench - Temporal Anticipation | 85 | Score (%) | 97.8 |
| OpenVLM MMBench V1.1 EN - Celebrity Recognition | 95.2 | Accuracy (%) | 97.5 |
| OpenVLM MMBench V1.1 CN - Celebrity Recognition | 94.6 | Accuracy (%) | 97.2 |
| OpenVLM MMT-Bench - LVLM Response Judgement | 65 | Score (%) | 96.4 |
| OpenVLM MMT-Bench - Spot The Similarity | 95 | Score (%) | 96.4 |
Interactive version: theaggregate.ai/model?slug=step-1-5v-mini · How It Works · Data refreshed daily, snapshot 2026-11-08.