List your company

General Language Understanding and Reasoning on HuggingFace Open LLM Leaderboard (Composite)

85.32HellaSwag AccuracySimPO
59.16465.954572.74579.5355Feb 26, 2025Mar 29, 2025Apr 30, 2025May 31, 2025Jul 2, 2025Aug 2, 2025Sep 3, 2025

Evaluation results

MethodLinks
SimPOBase Model=Mistral-7B-Instruct2025.0985.3256.6222.06—58.8771.47
DPOBase Model=Mistral-7B-Instruct2025.0984.5359.2742.76—63.3366.74
SimUAPOBase Model=Mistral-7B-Instruct2025.0984.2257.8830.63—60.6970.04
SFTBase Model=Mistral-7B-Instruct2025.0983.6759.0642.23—62.9666.87
UAPOBase Model=Mistral-7B-Instruct2025.0983.3957.7830.17—59.265.45
UAPOBase Model=Llama-3-8B-Instruct2025.0976.3464.3176.04—6855.25
DPOBase Model=Llama-3-8B-Instruct2025.0976.2364.6176.42—68.1955.5
SFTBase Model=Llama-3-8B-Instruct2025.0975.8863.7975.28—66.6351.56
SimPOBase Model=Llama-3-8B-Instruct2025.0975.2964.456.56—65.0964.09
SimUAPOBase Model=Llama-3-8B-Instruct2025.0971.8964.3271.57—67.6662.87
LCG-MultinomialNB-6kBase Model=Mistral-7b-v0.32025.026259.5140.5152.953.73—
LCG-DistilBERT-6kBase Model=Mistral-7b-v0.32025.0261.9959.5140.3352.2253.51—
LCG-DistilBERT-1kBase Model=Mistral-7b-v0.32025.0261.9459.2438.2951.6252.77—
Perplexity-6kBase Model=Mistral-7b-v0.32025.0261.6458.483751.8852.25—
LCG-MultinomialNB-6kBase Model=LLaMa3-8b2025.0261.6162.2353.7554.9558.14—
LCG-DistilBERT-6kBase Model=LLaMa3-8b2025.0261.4362.6754.2854.7858.29—
Alpaca-52kBase Model=Mistral-7b-v0.32025.0261.1857.7331.6153.0750.9—
Perplexity-6kBase Model=LLaMa3-8b2025.0261.1461.0950.8753.556.65—
SuperFiltering-10%Base Model=Mistral-7b-v0.32025.0260.9859.3435.7149.8351.47—
LCG-DistilBERT-1kBase Model=LLaMa3-8b2025.0260.9562.2652.9252.8257.23—
Mistral-7b-v0.3Base Model=Mistral-7b-v0.32025.0260.9458.9636.6248.8151.33—
Kmeans-6kBase Model=Mistral-7b-v0.32025.0260.8658.4535.152.0551.62—
Kmeans-6kBase Model=LLaMa3-8b2025.0260.8658.4535.153.0751.87—
Random-6kBase Model=Mistral-7b-v0.32025.0260.8358.7535.0353.0751.92—
Random-6kBase Model=LLaMa3-8b2025.0260.8358.7535.0353.0751.92—
LIMA-6kBase Model=Mistral-7b-v0.32025.0260.5859.3437.3151.1152.09—
LIMA-6kBase Model=LLaMa3-8b2025.0260.5862.1350.3451.1155.82—
Alpaca-52kBase Model=LLaMa3-8b2025.0260.5761.3646.152.4155.74—
SuperFiltering-10%Base Model=LLaMa3-8b2025.0260.3861.9550.3451.5455.36—
LLaMa3-8bBase Model=LLaMa3-8b2025.0260.1762.1350.4250.2649.98—