Model card
GPT-4V.
UnknownmultimodalUnknown paramsTransformer
GPT-4 with Vision. First major multimodal GPT-4 release, Sept 2023. Evaluated on MMMU, VQA, TextVQA. Source: GPT-4 Technical Report.
§ 02 · Benchmarks
Every benchmark GPT-4V has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | VQA v2.0 | Multimodal · Visual Question Answering | accuracy | 77.2% | #13 | 2023-03-15 | source ↗ |
| 02 | TextVQA | Multimodal · Visual Question Answering | accuracy | 78.0% | #16 | 2023-03-15 | source ↗ |
| 03 | MMBench | Multimodal · Visual Question Answering | accuracy | 75.8% | #17 | 2023-03-15 | source ↗ |
| 04 | MMMU | Multimodal · Visual Question Answering | accuracy | 56.8% | #25 | 2023-03-15 | 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.
§ 04 · Papers
1 paper with results for GPT-4V.
- 2023-03-15· Natural Language Processing· 4 results
GPT-4 Technical Report
§ 05 · Related models
Other Unknown models scored on Codesota.
CRAFT
Unknown params · 21 results
GPT-2-Large (fine-tuning)
Unknown params · 20 results
HTLM (fine-tuning)
Unknown params · 20 results
TextFuseNet (ResNeXt-101)
Unknown params · 16 results
MixNet
Unknown params · 13 results
PAN
Unknown params · 12 results
SPCNET
Unknown params · 12 results
TESTR
Unknown params · 12 results
§ 06 · Sources & freshness
Where these numbers come from.
arxiv
4
results
4 of 4 rows marked verified.