Zero-shot Accuracy on Reasoning Suite (PIQA, Hella Swag, LAMBADA, ARC-e, ARC-c, SciQ, Race, MMLU) benchmark leaderboard · SOTA2 Research

Zero-shot Accuracy on Reasoning Suite (PIQA, Hella Swag, LAMBADA, ARC-e, ARC-c, SciQ, Race, MMLU)

80.7PIQALlama3 8B

Evaluation Results

Method	Links
Llama3 8B2025.09		80.7	79.1	75.6	77.7	53.5	93.9	40.3	62.2	70.4
Qwen3 14B2025.09		79.9	78.9	67.9	82.8	60.2	96.5	43.3	77.2	73.3
Qwen3 8B2025.09		77.7	74.9	64.1	80.7	56.7	95.7	40.9	73	70.5
CoSpaDi2025.09		77.3	71.7	72	73.3	51.3	91.9	43.1	65.8	68.3
CoSpaDi2025.09		76.5	68	65.6	72.2	48.9	93.2	40.7	60.8	65.7
SVD-LLM2025.09		76.2	67.6	69.1	69.8	46.8	91	42.9	62.5	65.8
CoSpaDi2025.09		75.2	66.5	73.8	66.5	41.6	89.5	38.2	42.8	61.8
CoSpaDi2025.09		74.6	64.2	69	65.3	43.6	90.7	42.5	58	63.5
SVD-LLM2025.09		73.8	63.9	62.2	68.7	45.7	90.1	40.5	54.7	62.5
CoSpaDi2025.09		72.4	60.5	62.6	63.9	41.2	88.4	39.5	51.3	59.97
SVD-LLM2025.09		72	59.7	61.5	62.6	39.3	88.9	41.5	52	59.7
SVD-LLM2025.09		71.1	58.4	59.3	55.5	34	86.4	35.5	32.6	54.1
CoSpaDi2025.09		70.5	56.2	61.3	54.2	33.5	85.7	36.2	32.2	53.7
SVD-LLM2025.09		70.4	55.2	53.8	59.3	37.1	87.2	38.4	44.8	55.8
CoSpaDi2025.09		69.5	52.3	57.3	53.2	33	84.4	37.5	43.6	53.9
CoSpaDi2025.09		68.9	49	49.9	49.4	29.9	82	36.8	36.6	50.3
SVD-LLM2025.09		67.4	48.7	46	48.5	30.7	80.6	36.7	36.8	49.4
SVD-LLM2025.09		66.3	44.6	37.9	45	28.1	77.3	35.3	29.1	45.4
SVD-LLM2025.09		65.8	46.4	38.1	41.9	27.7	70	31.8	27.2	43.6
CoSpaDi2025.09		63.7	41.4	30.3	39.1	26.6	68.5	30.5	25.4	40.7
SVD-LLM2025.09		60.3	34.5	11.4	32.4	24.5	44.2	25.7	23.1	32