Model Merging

Benchmarks

Dataset Name	SOTA Method	Metric
8 Vision tasks (test)		Accuracy95.8	77	20d ago
Average of 8 benchmarks	Pico	Average Accuracy52.79	72	1mo ago
GLUE CoLA, MRPC, RTE, SST-2	Task arithmetic	Absolute Accuracy75.9	60	3mo ago
20-task vision merging scenario (test)		Accuracy94.7	44	20d ago
14-task vision merging scenario (test)		Accuracy94.3	44	20d ago
Language Benchmarks 5-task		Score0.63	44	20d ago
Large-scale tasks	DOGE AM	Average Normalized Accuracy98.2	36	1mo ago
Sustainability to large-scale tasks	DOGE AM	Average Normalized Accuracy91.4	24	1mo ago
Sustainability to large-scale tasks 2 tasks	DOGE AM	Average Normalized Accuracy101.2	24	1mo ago
7 NLP tasks (test)		Accuracy79.2	22	2mo ago
Large-scale tasks 16 tasks merged	DOGE AM	Average Normalized Accuracy91.5	12	1mo ago
Large-scale tasks 12 tasks merged	DOGE AM	Avg Normalized Acc94.3	12	1mo ago
Sustainability to large-scale tasks (20 tasks)	RegMean++	Average Normalized Accuracy82.9	12	1mo ago
Sustainability to large-scale 8 tasks	DOGE AM	Avg Normalized Accuracy94.8	12	1mo ago
Sustainability to large-scale tasks 4 tasks	DOGE AM	Average Accuracy98.3	12	1mo ago
LLM Evaluation Suite	KARCHER	Normalized Score0.401	12	2mo ago
Vision, Language, and Multi-modal tasks	Multiple Models	Parameters8	11	14d ago
Qwen3-4B-Base Transfer 8 benchmarks	Pico	Math Accuracy32.65	6	1mo ago
LLM Benchmark Family MMLU, TruthfulQA, BBQ, CNN/DailyMail	SA-Merging	MMLU Score69.87	5	1d ago

Showing 19 of 19 rows