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

Question Answering on TriQA

83.43Accuracy

CDKC

Updated 21d ago

Evaluation Results

Method	Links
CDKC 2026.02		83.43
GRPO 2026.02		82.63
CoT 2026.02		69.6
RAG 2026.02		69.1
CDKC 2026.02		68.23
GRPO 2026.02		66.7
CGKE 2026.02		66.47
Vanilla SFT 2026.02		64.83
Vanilla LLM 2026.02		63
RAG 2026.02		61.7
EMoE 2025.09		61.32
Top-k 2025.09		61.1
Top-k 2025.09		60.24
EMoE 2025.09		60.13
EMoE 2025.09		59.77
Top-k 2025.09		59.53
EMoE 2025.09		59.24
EMoE 2025.09		59.22
Top-k 2025.09		59.1
Top-k 2025.09		59.06
EMoE 2025.09		58.2
Top-k 2025.09		57.62
EMoE 2025.09		54.79
Top-k 2025.09		54.32
Llama-3.1 2026.01		52.1
EMoE 2025.09		52.07
EMoE 2025.09		51.58
CoT 2026.02		49.47
CGKE 2026.02		48.47
EMoE 2025.09		47.81
Vanilla SFT 2026.02		47.37
Top-k 2025.09		46.86
Top-k 2025.09		46.38
Vanilla LLM 2026.02		45.07
Top-k 2025.09		41.36
EMoE 2025.09		41.27
EMoE 2025.09		39.64
Top-k 2025.09		39.1
Top-k 2025.09		38.98
EMoE 2025.09		34.84
Top-k 2025.09		32.04
A3 2026.01		19.4
DiffuLlama 2026.01		18.5
Dream 2026.01		18.3
A3 2026.01		15.9
A3 2026.01		10.2
Plaid 2026.01		1.2