InternVL3.5-1B-Instruct: benchmark results
Provider: Shanghai AI Lab. Released 2025-08-26. Access: Open.
Aggregate Rating 1285 ± 45, rank #8916 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA Multi - ruCommonVQA | 13.5 | Score (%) | 28.8 |
| MERA Multi - ruNaturalScienceVQA | 0.6 | Score (%) | 24.6 |
| MERA Multi - Image | 1.6 | Score (%) | 20.3 |
| MERA Multi - RealVideoQA | 17.1 | Score (%) | 19 |
| MERA Multi - LabTabVQA | 0.1 | Score (%) | 18.6 |
| MERA Multi - SchoolScienceVQA | 0.2 | Score (%) | 18.6 |
| MERA Multi - ruMathVQA | 0.6 | Score (%) | 17.8 |
| MERA Multi - Video | 13.7 | Score (%) | 16.7 |
| MERA Multi - ruHHH-Video | 9.7 | Score (%) | 16.7 |
| MERA Multi - CommonVideoQA | 14.3 | Score (%) | 14.3 |
| MERA Multi - UniScienceVQA | 0.2 | Score (%) | 13.6 |
| MERA Multi - ruCLEVR | 0.5 | Score (%) | 11 |
Interactive version: theaggregate.ai/model?slug=internvl3-5-1b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.