Share your thoughts, 1 month free Claude Pro on usSee more

Zero-shot Reasoning on (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA)

82.813BoolQ Accuracy (Zero-shot)

Vicuna-13B-v1.3 (Original)

Updated 29d ago

Evaluation Results

Method
Vicuna-13B-v1.3 (Original) 2025.02	82.813	78.346	77.017	71.113	75.547	47.611	45.4	68.264
FLAP 2025.02	81.1	76.77	73.72	68.35	71.51	42.49	41	64.991
Sliding-Window Merging 2025.02	81.04	76.442	74.846	70.324	71.801	44.625	41.8	65.84
LLaMA-2-13B (Original) 2025.02	80.55	79.053	79.367	72.139	79.377	49.147	45.2	69.262
Wanda-sp 2025.02	77.09	77.09	74.42	67.96	67.8	42.32	42.8	64.211
Vicuna1.5-7B 2026.03	75.75	77.8	71.02	67.64	69.02	40.87	42.4	63.5
Shortened-LLM 2025.02	75.535	77.476	73.571	68.272	72.18	44.198	43.2	64.919
FLAP 2025.02	75.17	73.99	65.54	67.56	61.32	36.77	37.4	59.679
LLM-Pruner 2025.02	74.526	78.346	72.426	69.219	69.739	40.529	43.2	63.998
FLAP 2025.02	72.78	74.65	69.07	68.35	70.83	40.61	40	62.327
LLM-Pruner 2025.02	71.315	79.162	74.836	67.324	73.485	43.771	41.6	64.499
FLAP 2025.02	71.25	69.59	61.68	64.4	59.05	34.13	36	56.586
LLM-Pruner 2025.02	70.581	76.659	67.317	65.272	63.258	35.154	40.8	59.863
Wanda-sp 2025.02	69.63	77.48	74.75	67.01	73.48	44.11	44	64.351
GPrune-LLM (Wanda-sp) 2026.03	69.51	75.68	67.51	64.09	66.37	38.48	40.2	60.26
Sliding-Window Merging 2025.02	69.45	74.918	67.447	63.378	66.414	38.311	37.4	59.617
LLaMA2 13B 2026.03	68.99	79.05	76.6	69.77	73.32	45.56	42	65.04
Shortened-LLM 2025.02	68.532	74.102	66.421	64.009	67.593	41.126	38.6	60.055
Shortened-LLM 2025.02	68.318	76.279	75.204	71.113	74.79	46.672	42.4	64.968
GPrune-LLM (FLAP) 2026.03	67.8	75.63	66.7	63.46	66.96	38.05	41	59.94
Wanda-sp 2026.03	67.31	74.16	65.21	61.8	66.96	38.31	39.8	59.08
GPrune-LLM (Wanda-sp) 2026.03	66.97	73.29	62.12	61.97	61.49	36.86	39	57.39
FLAP 2026.03	66.88	72.47	63.17	64.48	63.55	34.81	39.8	57.88
FLAP 2026.03	66.18	69.86	57.56	62.35	59.97	33.11	38.4	55.35
LLM-Pruner 2025.02	66.086	76.061	67.785	59.195	67.382	39.334	41.8	59.663
GPrune-LLM (FLAP) 2026.03	64.34	73.67	62.55	60.46	64.81	37.63	40.4	57.69
Sliding-Window Merging 2025.02	64.006	77.421	76.369	71.665	76.557	48.549	43.8	65.481
Shortened-LLM 2025.02	63.333	72.307	67.128	63.694	66.667	39.761	37	58.556
SLEB 2025.02	63.211	76.061	70.116	65.43	70.749	39.932	39.2	60.671
FLAP 2026.03	62.66	65.02	48.95	57.85	47.43	31.48	37	50.06
LLM-Pruner 2026.03	62.39	34.12	53.35	35.82	27.82	34	43.96	-
SLEB 2025.02	62.385	70.62	58.415	55.643	62.5	36.689	33.8	54.293
SLEB 2025.02	62.385	70.62	58.415	55.643	62.5	36.689	33.8	54.293
GPrune-LLM (FLAP) 2026.03	62.26	67.08	52.83	54.7	50.04	31.91	37.6	50.92
FLAP 2026.03	62.08	52.98	36.9	52.25	38.05	27.39	34.8	43.49
GPrune-LLM (Wanda-sp) 2026.03	61.99	67.95	54.17	54.62	53.03	33.45	39.6	52.12
Wanda-sp 2026.03	61.68	53.48	26.48	49.64	27.74	24.91	30.6	39.22
GPrune-LLM (Wanda-sp) 2026.03	61.65	61.43	42.01	52.01	38.22	28.24	35.6	45.59
Wanda-sp 2025.02	61.65	71.22	63.96	61.4	57.49	35.32	37	55.434
Wanda-sp 2026.03	61.16	53.05	26.65	49.49	29	26.19	29.6	39.31
Wanda-sp 2026.03	60.83	56.64	27.38	50.12	29.12	23.04	31.2	39.76
Sliding-Window Merging 2025.02	59.939	73.286	68.751	65.983	68.981	41.724	39	59.666
Wanda-sp 2025.02	59.02	55.11	33.58	52.8	29.84	24.91	28.6	40.551
GPrune-LLM (FLAP) 2026.03	58.65	62.51	41.58	52.57	43.27	29.44	35.2	46.17
GPrune-LLM (FLAP) 2026.03	56.64	56.58	30.45	50.28	37.92	25.85	33.2	41.56
GPrune-LLM (Wanda-sp) 2026.03	53.79	63.98	43.67	54.85	45.45	29.44	36	46
GPrune-LLM (FLAP) 2026.03	52.08	65.34	44.05	53.59	52.69	29.01	35.2	47.42
GPrune-LLM (Wanda-sp) 2026.03	51.28	56.04	30.77	51.78	32.03	28.32	32.2	40.35
Wanda-sp 2026.03	51.16	52.67	26.09	47.51	26.6	27.39	29.2	37.23
LLM-Pruner 2026.03	50.98	75.84	64.14	59.83	66.12	38.65	40	56.51
Wanda-sp 2026.03	44.01	71.33	57.85	56.51	62.21	37.12	38.8	52.55
LLM-Pruner 2026.03	43.94	73.45	56.13	57.3	58.89	34.3	38.2	51.74
FLAP 2026.03	38.5	63.22	41.22	53.28	46.97	29.35	34.6	43.88
SLEB 2025.02	37.829	51.034	25.503	50.908	26.221	27.218	27.4	35.159
FLAP 2026.03	37.74	53.23	25.95	48.78	27.48	28.92	29.6	35.96