General NLP Evaluation on Natural Language Benchmarks Aggregate benchmark leaderboard · SOTA2 Research

General NLP Evaluation on Natural Language Benchmarks Aggregate

62.31Average ScoreDense

Evaluation Results

Method	Links
Dense2024.03		62.31	100
Dense2024.03		57.67	100
Dense2024.03		55.14	100
ShortGPT2024.03		54.43	87.35
LaCo2024.03		53.43	85.75
ShortGPT2024.03		50.53	91.64
RWKV-7B2024.03		50.37	100
ShortGPT2024.03		49.08	85.1
Dense2024.03		47.78	100
LaCo2024.03		47.62	86.36
ShortGPT2024.03		43.94	87.23
LaCo2024.03		42.93	74.44
LLMPrun.2024.03		41.76	72.41
ShortGPT2024.03		41.24	86.31
Mamba-2.8B2024.03		41.12	100
ShortGPT2024.03		40.38	80.17
LLMPrun.2024.03		39.2	62.91
ShortGPT2024.03		39.08	95.04
LLMPrun.2024.03		38.97	70.67
LaCo2024.03		38.41	80.39
ShortGPT2024.03		38.36	93.29
ShortGPT2024.03		37.18	90.42
ShortGPT2024.03		36.85	73.16
ShortGPT2024.03		35.59	86.55
SliceGPT2024.03		34.85	63.2
LLMPrun.2024.03		34.78	72.79
ShortGPT2024.03		33.82	67.14
SliceGPT2024.03		32.84	68.73
SliceGPT2024.03		26.23	45.48
SliceGPT2024.03		25.23	40.49