Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
In-Context Learning Stability Analysis on UniICL-Bench (test)
Loading...
2.1
Random Replace Error (Und.)
UniICL
1.496
5.573
9.65
13.727
Mar 25, 2026
Random Replace Error (Und.)
Random Replace Error (Gen.)
Reverse Order Error (Und.)
Reverse Order Error (Gen.)
Interference Error (Und.)
Interference Error (Gen.)
Average Perturbation Error (Und.)
Average Perturbation Error (Gen.)
Updated 22d ago
Evaluation Results
Method
Method
Links
Random Replace Error (Und.)
Random Replace Error (Gen.)
Reverse Order Error (Und.)
Reverse Order Error (Gen.)
Interference Error (Und.)
Interference Error (Gen.)
Average Perturbation Error (Und.)
Average Perturbation Error (Gen.)
UniICL
2026.03
2.1
10.3
1.4
6.1
1.6
3.4
1.7
6.6
BAGEL
2026.03
7.1
22
2.8
10.9
7.9
7.8
5.9
13.6
MLLM Avg.
2026.03
7.3
-
1.8
-
6.3
-
5.1
-
Unified Avg.
2026.03
17.2
15.7
8.5
5.7
11.3
10.4
12.4
10.6
Feedback
Search any
task
Search any
task