Idefics3-8B-Llama3: benchmark results
Provider: HuggingFace. Released 2024-08-05. Access: Open.
Aggregate Rating 1402 ± 18, rank #5993 of 10916 rated models, from 539 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Whoops | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Chart To Text | 100 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Table Structure Recognition | 100 | Score (%) | 94.7 |
| OpenVLM MMT-Bench - Logo and Brand Recognition | 100 | Score (%) | 94.4 |
| OpenVLM MME - Scene | 166.8 | Score | 94.2 |
| OpenVLM MMT-Bench - Celebrity Recognition | 95 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Color Constancy | 71.4 | Score (%) | 94.2 |
| OpenVLM MMT-Bench - Animated Character Recognition | 70 | Score (%) | 93.7 |
| OpenVLM MME - Color | 190 | Score | 93.4 |
| OpenVLM MMT-Bench - Temporal Ordering | 40 | Score (%) | 92 |
| OpenVLM MMT-Bench - Temporal Anticipation | 80 | Score (%) | 91.3 |
| OpenVLM MMT-Bench - Spot The Similarity | 90 | Score (%) | 90.8 |
Interactive version: theaggregate.ai/model?slug=idefics3-8b-llama3 · How It Works · Data refreshed daily, snapshot 2026-11-08.