Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge & Reasoning on MMLU-Redux
Loading...
79.8
Accuracy
Sigma-MoE-Tiny
49.536
57.393
65.25
73.107
Dec 18, 2025
Dec 22, 2025
Dec 26, 2025
Dec 30, 2025
Jan 3, 2026
Jan 7, 2026
Jan 12, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Sigma-MoE-Tiny
Architecture=MoE, # Ac...
2025.12
79.8
Phi-3.5-MoE
Architecture=MoE, # Ac...
2025.12
78.6
Qwen3-1.7B
Architecture=Dense, #...
2025.12
73.9
DeepSeek-R1-Distill-Qwen-7B
Architecture=Dense, #...
2025.12
68.5
DeepSeek-R1-Distill-Llama-8B
Architecture=Dense, #...
2025.12
66.4
Engram-40B
Shots=5-shot
2026.01
64.5
Engram-27B
Shots=5-shot
2026.01
64
MoE-27B
Shots=5-shot
2026.01
60.6
Dense-4B
Shots=5-shot
2026.01
50.7
Feedback
Search any
task
Search any
task