Yi-VL-34B: benchmark results
Provider: 01.AI. Released 2024-01-23. Access: Open.
Aggregate Rating 1376 ± 26, rank #6979 of 10916 rated models, from 461 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Temporal Ordering | 50 | Score (%) | 99.3 |
| OpenVLM COCO Captions | 98.5 | CIDEr | 99 |
| OpenVLM A-Bench - Nouns as Adjectives | 86 | Accuracy (%) | 97.2 |
| OpenVLM MME - Scene | 167.2 | Score | 95.7 |
| OpenVLM MMBench V1.1 EN - Image Topic | 98.9 | Accuracy (%) | 95.2 |
| OpenVLM MME - Position | 168.3 | Score | 94.2 |
| OpenVLM MMT-Bench - Pixel Localization | 45 | Score (%) | 93 |
| OpenVLM MMT-Bench - Raven Progressive Matrices | 30 | Score (%) | 88.8 |
| OpenVLM MMT-Bench - Temporal Sequence Understanding | 50 | Score (%) | 88.1 |
| CMMMU | 36.5 | Test Overall (%) | 87.5 |
| OpenVLM MMT-Bench - Social Relation Recognition | 65 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Multiple Image Captioning | 95 | Score (%) | 86.9 |
Interactive version: theaggregate.ai/model?slug=yi-vl-34b · How It Works · Data refreshed daily, snapshot 2026-11-08.