Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Language Modeling on LiveBench
Loading...
31.1
Accuracy
Qwen2.5-7B
1.876
9.463
17.05
24.637
Jun 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-7B
Model=Qwen2.5-7B
2026.06
31.1
Llama3.1-8B
Model=Llama3.1-8B
2026.06
19.7
Qwen2.5-0.5B
Model=Qwen2.5-0.5B
2026.06
12.1
Uni-Energy
Backbone=LLaDa-8B
2026.06
10.9
Uni-Energy
Backbone=Dream-7B
2026.06
9.9
Ind-Energy
Backbone=Dream-7B
2026.06
9.3
Inv-Energy
Backbone=Dream-7B
2026.06
8.8
Ind-Energy
Backbone=LLaDa-8B
2026.06
8.6
APD
Backbone=Dream-7B, rep...
2026.06
8.2
DAWN
Backbone=Dream-7B, rep...
2026.06
7.3
Dream-7B
Model=Dream-7B, reprod...
2026.06
7.1
CORE
Backbone=Dream-7B, rep...
2026.06
6.5
APD
Backbone=LLaDa-8B, rep...
2026.06
6.3
Inv-Energy
Backbone=LLaDa-8B
2026.06
5.7
DAWN
Backbone=LLaDa-8B, rep...
2026.06
4.8
LLaDa-8B
Model=LLaDa-8B, reprod...
2026.06
4.1
CORE
Backbone=LLaDa-8B, rep...
2026.06
3
Feedback
Search any
task
Search any
task