Codesota · Models · Llama 3-V (405B)4 results · 4 benchmarks
Model card
Llama 3-V (405B).
unknown
§ 02 · Benchmarks
Every benchmark Llama 3-V (405B) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | TextVQA | Multimodal · Visual Question Answering | accuracy | 84.8% | #5 | — | source ↗ |
| 02 | VQA v2.0 | Multimodal · Visual Question Answering | accuracy | 80.2% | #8 | — | source ↗ |
| 03 | DocVQA | Computer Vision · Document Understanding | anls | 92.6% | #12 | — | source ↗ |
| 04 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 64.5% | #20 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Llama 3-V (405B) actually performs.
§ 04 · Papers
1 paper with results for Llama 3-V (405B).
- 2024-07-31· 4 results
The Llama 3 Herd of Models
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
4
results
0 of 4 rows marked verified.