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

Multitask Language Understanding on C-MMLU (Accuracy)

51.2Accuracy (C-MMLU)

Meta-Llama-3-8B

Updated 1mo ago

Evaluation Results

Method	Links
Meta-Llama-3-8B 2026.02		51.2
RouterDC 2026.02		51
RouterDC + RACER-G (w/ Agg.) 2026.02		50.7
RouterDC + RACER-P (w/ Agg.) 2026.02		50.6
Chinese-Mistral-7B-v0.1 2026.02		49.1
KNNR + RACER-P (w/ Agg.) 2026.02		49
KNNR + RACER-G (w/ Agg.) 2026.02		48.8
MLPR + RACER-P (w/ Agg.) 2026.02		48.4
MLPR + RACER-G (w/ Agg.) 2026.02		48.3
KNNR 2026.02		48.1
Mistral-7B-v0.1 2026.02		44.6
MetaMath-Mistral-7B 2026.02		44.4
MLPR 2026.02		44.4
Dolphin-2.6-Mistral-7b 2026.02		44.2
Dolphin-2.9-Llama3-8b 2026.02		43.9
Zephyr-7b-beta 2026.02		43.5