Question Answering on TruthfulQA 1.0 (test) benchmark leaderboard · SOTA2 Research

Question Answering on TruthfulQA 1.0 (test)

88% True (GPT-Judge)CoT with SSRAG

Evaluation Results

Method	Links
CoT with SSRAG2026.01		88	81.2	87.1	0.18
SSRAG2026.01		87	82.3	86.4	0.18
CoVe with SSRAG2026.01		83	77	83	0.15
SSRAG2026.01		83	75.2	82.4	0.23
SSRAG2026.01		82	85.2	91.6	0.29
CoT with SSRAG2026.01		81	83.4	82	0.16
SSRAG2026.01		79	79.8	89.1	0.19
SSRAG2026.01		75	81.1	91	0.27
Graph RAG2026.01		67	58	65	0.4
Graph RAG2026.01		65	59.8	68	0.38
CoVe with Graph2026.01		64	57.7	57.9	0.42
CoT with Graph RAG2026.01		63	54.7	62.7	0.37
CoVe2026.01		58	48	41.1	0.47
Baseline RAG2026.01		57	43.2	47	0.51
CoT2026.01		57	47	45.4	0.47
Baseline RAG2026.01		56	50	55	0.49
Baseline RAG2026.01		52	52.1	52	0.52
CoT2026.01		52	49.2	47.3	0.51
Baseline RAG2026.01		52	51.4	53	0.45
Baseline RAG2026.01		47	32.1	41	0.54