Cambrian-34B: benchmark results
Provider: NYU. Released 2024-06-24. Access: Open.
Aggregate Rating 1421 ± 28, rank #5127 of 10916 rated models, from 256 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM SEEDBench IMG - Instance Interaction | 80.4 | Accuracy (%) | 96 |
| OpenVLM MMBench V1.1 CN - Function Reasoning | 95.6 | Accuracy (%) | 95.4 |
| OpenVLM MMMU - Diagnostics and Laboratory Medicine | 53.3 | Accuracy (%) | 95.1 |
| OpenVLM OCR-VQA | 68.2 | Accuracy (%) | 93.2 |
| OpenVLM LLaVA-Bench - Conv | 94 | Score | 90.6 |
| OpenVLM MMBench V1.1 CN - Image Topic | 98.9 | Accuracy (%) | 90.3 |
| OpenVLM MME - Existence | 200 | Score | 89.7 |
| OpenVLM MMBench V1.1 EN - Image Emotion | 82.2 | Accuracy (%) | 88.7 |
| OpenVLM VCR - English Easy | 87.7 | Jaccard (%) | 88.7 |
| OpenVLM MME - Posters | 184.7 | Score | 88 |
| OpenVLM A-Bench - Aesthetic Quality | 66.7 | Accuracy (%) | 87.1 |
| OpenVLM MMMU - Design | 83.3 | Accuracy (%) | 86.7 |
Interactive version: theaggregate.ai/model?slug=cambrian-34b · How It Works · Data refreshed daily, snapshot 2026-11-08.