📊 Showing 8 results | 📏 Metric: Accuracy
Rank | Model | Paper | Accuracy | Date | Code |
---|---|---|---|---|---|
1 | GPT-4V | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 24.00 | 2024-01-11 | 📦 cvndsh/rebus |
2 | Gemini Pro | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 13.20 | 2024-01-11 | 📦 cvndsh/rebus |
3 | LLaVa-1.5-13B | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 1.80 | 2024-01-11 | 📦 cvndsh/rebus |
4 | LLaVa-1.5-7B | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 1.50 | 2024-01-11 | 📦 cvndsh/rebus |
5 | BLIP2-FLAN-T5-XXL | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 0.90 | 2024-01-11 | 📦 cvndsh/rebus |
6 | CogVLM | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 0.90 | 2024-01-11 | 📦 cvndsh/rebus |
7 | QWEN | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 0.90 | 2024-01-11 | 📦 cvndsh/rebus |
8 | InstructBLIP | REBUS: A Robust Evaluation Benchmark of Understanding Symbols | 0.60 | 2024-01-11 | 📦 cvndsh/rebus |