Eagle-X5-13B: benchmark results
Provider: NVIDIA. Released 2024-10-17. Access: Open.
Aggregate Rating 1345 ± 33, rank #7846 of 10916 rated models, from 439 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Geometrical Perspective | 100 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Order Hallucination | 65 | Score (%) | 99 |
| OpenVLM POPE | 89.8 | Overall (%) | 96.7 |
| OpenVLM MMT-Bench - Deepfake Detection | 65 | Score (%) | 93.7 |
| OpenVLM MMT-Bench - Single Object Tracking | 70 | Score (%) | 93.4 |
| OpenVLM MMT-Bench - Other Biological Attributes | 85 | Score (%) | 93.2 |
| OpenVLM MMT-Bench - VI | 65.4 | Score (%) | 91.7 |
| OpenVLM MMT-Bench - Micro Expression Recognition | 40 | Score (%) | 89.8 |
| OpenVLM MMT-Bench - Meme Image Understanding | 95 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - Set-of-Mark Recognition | 94.7 | Score (%) | 88.6 |
| OpenVLM MMT-Bench - CIM | 70 | Score (%) | 88.1 |
| OpenVLM MMT-Bench - Temporal Sequence Understanding | 50 | Score (%) | 88.1 |
Interactive version: theaggregate.ai/model?slug=eagle-x5-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.