TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Long-Context Understanding/MMNeedle

Long-Context Understanding on MMNeedle

Metric: 10 Images, 4*4 Stitching, Exact Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕10 Images, 4*4 Stitching, Exact Accuracy▼Extra DataPaperDate↕Code
1GPT-4o26.9NoGPT-4 Technical Report2023-03-15Code
2GPT-4V7.58NoGPT-4 Technical Report2023-03-15Code
3Gemini Pro 1.56.09NoGemini 1.5: Unlocking multimodal understanding a...2024-03-08Code
4Gemini Pro 1.00.4NoGemini: A Family of Highly Capable Multimodal Mo...2023-12-19Code
5Claude 3 Opus0.4No---
6LLaVA-Llama-30No--Code
7IDEFICS2-8B0No---
8InstructBLIP-Flan-T5-XXL0No--Code
9CogVLM2-Llama-30No--Code
10mPLUG-Owl-v20No--Code
11CogVLM-17B0No--Code
12InstructBLIP-Vicuna-13B0No--Code