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

Mathematical Reasoning on GSM8K (Acc, pass@5)

80.64Accuracy

Llama-3-8B-Instruct

Updated 1mo ago

Evaluation Results

Method	Links
Llama-3-8B-Instruct 2026.06		80.64	88.23
Qwen2.5-7B 2026.06		79.28	87.64
Med42-Llama3-8B 2026.06		77.06	85.8
Llama-3-8B-Instruct 2026.06		75.82	83.47
Qwen2.5-7B 2026.06		73.47	81.83
Med42-Llama3-8B 2026.06		71.89	80.14
Qwen2.5-Med-7B 2026.06		71.35	80.63
ReLAR 2026.06		71.28	84.2
ReLAR 2026.06		68.45	78.23
MedGemma-4B 2026.06		66.71	75.29
Qwen2.5-Med-7B 2026.06		64.41	73.85
Mistral-7B-Instruct 2026.06		63.82	82.47
MedGemma-4B 2026.06		61.18	70.32
Mistral-7B-v0.3 2026.06		57.84	79.36
Gemma-7B 2026.06		56.28	76.43
Med42-Mistral-7B 2026.06		54.82	81.47
Mistral-7B-Instruct 2026.06		53.47	74.83
Gemma-7B 2026.06		47.63	68.84
Med42-Mistral-7B 2026.06		46.53	72.84
Mistral-7B-v0.3 2026.06		40.63	67.84
LLaMA-2-7B 2026.06		30.56	48.73
Falcon-7B 2026.06		25.63	36.82
LLaMA-2-7B 2026.06		23.82	31.47
Falcon-7B 2026.06		17.84	24.47