Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multitask Language Understanding on MMLU Korean (test)
Loading...
72
Accuracy
Trinity Large
24.16
36.58
49
61.42
Feb 16, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Trinity Large
Architecture=MoE, Eval...
2026.02
72
Qwen3
Size=8B, Evaluation Mo...
2026.02
64
Qwen3
Size=4B, Evaluation Mo...
2026.02
59
TrillionLabs
Size=7B, Evaluation Mo...
2026.02
50
Datology
Size=8B, Evaluation Mo...
2026.02
49
Llama-3.1
Size=8B, Evaluation Mo...
2026.02
48
Granite-4.0
Size=Micro, Evaluation...
2026.02
46
SmolLM3
Size=3B, Evaluation Mo...
2026.02
45
LFM2.5
Size=1.2B, Evaluation...
2026.02
44
Datology
Size=3B, Evaluation Mo...
2026.02
43
Llama-3.2
Size=3B, Evaluation Mo...
2026.02
39
Llama-3.2
Size=1B, Evaluation Mo...
2026.02
26
Feedback
Search any
task
Search any
task