Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reading Comprehension on TibetanQA
Loading...
59.19
Exact Match (EM)
Ours-MoE-SFT
7.9076
21.2213
34.535
47.8487
Jul 12, 2025
Exact Match (EM)
F1 Score
Updated 20d ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
F1 Score
Ours-MoE-SFT
Model=Ours-MoE-SFT
2025.07
59.19
74.37
Ours-Base
Model=Ours-Base
2025.07
49.43
66.15
Ours-SFT
Model=Ours-SFT
2025.07
46.15
63.15
Ours-Base-32k
Model=Ours-Base-32k
2025.07
38.42
55.52
LLaMA3.1-8B-Instruct
Model=LLaMA3.1-8B-Inst...
2025.07
36.09
53.04
Ours-MoE-Base
Model=Ours-MoE-Base
2025.07
29.62
45.7
Ours-MoE-Base-8k
Model=Ours-MoE-Base-8k
2025.07
28.87
43.56
Qwen2.5-7B-base
Model=Qwen2.5-7B-base
2025.07
19.31
32.38
Qwen3-8B
Model=Qwen3-8B
2025.07
17.8
30.22
Qwen2.5-7B-Instruct
Model=Qwen2.5-7B-Instruct
2025.07
10.15
18.42
DeepSeek-R1-Distill-Llama-8B
Model=DeepSeek-R1-Dist...
2025.07
9.88
17.99
Feedback
Search any
task
Search any
task