Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Financial Task on Headline
Loading...
86.2
Performance
DSIR
73.512
76.806
80.1
83.394
Nov 10, 2025
Performance
Updated 1mo ago
Evaluation Results
Method
Method
Links
Performance
DSIR
Model=LLAMA3-8B-INSTRUCT
2025.11
86.2
NTK-Selector
Model=LLAMA3-8B-INSTRUCT
2025.11
86.2
LESS
Model=LLAMA3-8B-INSTRUCT
2025.11
85.9
Gradient
Model=LLAMA3-8B-INSTRUCT
2025.11
85.4
Random
Model=LLAMA3-8B-INSTRUCT
2025.11
85.2
TSDS
Model=LLAMA3-8B-INSTRUCT
2025.11
85
Embedding
Model=LLAMA3-8B-INSTRUCT
2025.11
83.7
NTK-Selector
Model=QWEN3-8B
2025.11
83.4
Domain-Only
Model=LLAMA3-8B-INSTRUCT
2025.11
82.4
Gradient
Model=QWEN3-8B
2025.11
82.3
DSIR
Model=QWEN3-8B
2025.11
82.3
TSDS
Model=QWEN3-8B
2025.11
81.9
Embedding
Model=QWEN3-8B
2025.11
81.8
LESS
Model=QWEN3-8B
2025.11
81.8
Random
Model=QWEN3-8B
2025.11
80.9
Base
Model=LLAMA3-8B-INSTRUCT
2025.11
78.5
Domain-Only
Model=QWEN3-8B
2025.11
75.3
Base
Model=QWEN3-8B
2025.11
74
Feedback
Search any
task
Search any
task