Stable Diffusion v2.1

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)	1	▇▇▇▇▇▇ 20%	CC-BY-4.0
GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1	1	▇▇▇▇▇▇ 20%	MIT (README); CC-BY-4.0 (arXiv 2310.11513v1)
EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)	1	▇▇▇▇▇▇ 19%	CC-BY-4.0
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty (arXiv v1)	1	▇▇▇▇▇ 15%	CC-BY-4.0
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3)	1	▇▇▇▇ 13%	CC-BY-4.0
Evaluating Numerical Reasoning in Text-to-Image Models (GeckoNum, arXiv v3)	1	▇▇ 7%	CC-BY-4.0
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)	1	▇▇ 5%	CC-BY-SA-4.0
prior · pull toward the middle		▇ 1%
weighted average		= 29.3