Zero-shot Evaluation on German LLM Evaluation Suite (MMLU, ARC, Hellaswag, LAMBADA, OBQA) benchmark leaderboard · SOTA2 Research

Zero-shot Evaluation on German LLM Evaluation Suite (MMLU, ARC, Hellaswag, LAMBADA, OBQA)

31.06MMLUDENSE-CORE 1B

Evaluation Results

Method	Links
DENSE-CORE 1B2026.04		31.06	35.99	57.3	48.69	42.8	48.48	44.05
Gemma-3-1B2026.04		30.01	30.55	47.89	43.43	41.71	45.05	39.77
DENSE-CORE 1B2026.04		29.88	32.99	54.64	45.51	40.29	48.49	41.97
LLäMmlein-1B2026.04		29.26	30.27	48.19	44.8	44.89	47.27	40.78
DENSE-CORE 350M2026.04		28.97	31.4	50.55	41.1	37.55	45.86	39.24
Llama-3.2-1B2026.04		28.58	29.9	40.51	40.07	44.31	44.04	37.9
RANDOM 1B2026.04		27.28	27.46	43.97	41.6	38.84	41.82	36.83
RANDOM 350M2026.04		27.13	26.15	41.1	37.18	33.52	41.01	34.35