Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conversational Question Answering on QuAC 3,000 3
Loading...
56.2
Accuracy
SINKTRACK
35.5456
40.9078
46.27
51.6322
Apr 11, 2026
Accuracy
Macro F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Macro F1 Score
SINKTRACK
Model=Llama3.1-8B-Inst...
2026.04
56.2
53.45
Direct
Model=Llama3.1-8B-Inst...
2026.04
53.7
51.2
SINKTRACK
Model=Qwen2.5-7B-Instr...
2026.04
52.01
47.77
Direct
Model=Qwen2.5-7B-Instr...
2026.04
51.26
47.64
CoT
Model=Llama3.1-8B-Inst...
2026.04
49.13
34.47
SINKTRACK
Model=MiniCPM3-4B, Pro...
2026.04
48.53
49.75
Direct
Model=MiniCPM3-4B, Pro...
2026.04
48.13
49.53
CoT
Model=MiniCPM3-4B, Pro...
2026.04
39.39
41.19
CoT
Model=Qwen2.5-7B-Instr...
2026.04
36.34
37.92
Feedback
Search any
task
Search any
task