OpenCodePapers

multimodal-reasoning-on-rebus

Multimodal Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link24.0GPT-4V2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link13.2Gemini Pro2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link1.8LLaVa-1.5-13B2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link1.5LLaVa-1.5-7B2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link0.9BLIP2-FLAN-T5-XXL2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link0.9CogVLM2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link0.9QWEN2024-01-11
REBUS: A Robust Evaluation Benchmark of Understanding Symbols✓ Link0.6InstructBLIP2024-01-11