Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long narrative understanding QA on NarrativeQA (Acc %)
Loading...
55
Accuracy
HGMEM
32.12
38.06
44
49.94
Dec 30, 2025
Accuracy
Updated 3mo ago
Evaluation Results
Method
Method
Links
Accuracy
HGMEM
Base LLM=GPT-4o, Type=...
2025.12
55
ComoRAG
Base LLM=GPT-4o, Type=...
2025.12
54
GraphRAG
Base LLM=GPT-4o, Type=...
2025.12
53
NaiveRAG
Base LLM=GPT-4o, Type=...
2025.12
52
HGMEM
Base LLM=Qwen2.5-32B-I...
2025.12
51
DeepRAG
Base LLM=GPT-4o, Type=...
2025.12
45
LightRAG
Base LLM=GPT-4o, Type=...
2025.12
44
GraphRAG
Base LLM=Qwen2.5-32B-I...
2025.12
44
DeepRAG
Base LLM=Qwen2.5-32B-I...
2025.12
44
ComoRAG
Base LLM=Qwen2.5-32B-I...
2025.12
44
LightRAG
Base LLM=Qwen2.5-32B-I...
2025.12
40
NaiveRAG
Base LLM=Qwen2.5-32B-I...
2025.12
37
HippoRAG v2
Base LLM=GPT-4o, Type=...
2025.12
34
HippoRAG v2
Base LLM=Qwen2.5-32B-I...
2025.12
33
Feedback
Search any
task
Search any
task
