MiniCPM-V 4.6 1.3B — benchmark results
OpenBMB's Apache-2.0 1.3B on-device vision model (May 2026) pairing SigLIP2-400M with Qwen3.5-0.8B for image, multi-image, and video input. Provider: OpenBMB. Released 2026-05-11. Access: Open.
Unified ELO 1416 ± 61, rank #1149 of 1776 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 87.72 | Accuracy (%) | 81.8 |
| AA Humanity's Last Exam | 4.91 | Accuracy (%) | 31.2 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA Omniscience - Software Engineering (SWE) - Dart | 14 | Accuracy (%) | 27 |
| AA Omniscience - Software Engineering (SWE) - Julia | 4 | Accuracy (%) | 23.7 |
| AA-LCR | 6.3 | Score (self-reported) | 23.3 |
| AA Long Context Reasoning | 6.33 | Accuracy (%) | 17.6 |
| Tau3 Banking | 4.33 | Success Rate (%) | 15.3 |
| AA Omniscience - Software Engineering (SWE) - Python | 9 | Accuracy (%) | 12.9 |
| Artificial Analysis Intelligence Index | 4.19 | Intelligence Index | 12 |
| AA Omniscience - Software Engineering (SWE) - R | 2 | Accuracy (%) | 11.9 |
Interactive version: theaggregate.ai/model?slug=minicpm-v-4-6-1-3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.