Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-task Language Understanding on MMLU Pro (Score)
Loading...
82.6
MMLU Pro Score
Qwen3-Next-80B-A3B-Think
70.12
73.36
76.6
79.84
May 6, 2026
MMLU Pro Score
Updated 26d ago
Evaluation Results
Method
Method
Links
MMLU Pro Score
Qwen3-Next-80B-A3B-Think
Active=3B, Total=80B
2026.05
82.6
Intellect-3
Active=12B, Total=106B
2026.05
82.3
Mistral-Small-4-119B
Active=6B, Total=119B
2026.05
81.6
Nemotron-3-Nano-30B-A3B
Active=3B, Total=30B
2026.05
78.9
OLMo-3.1-32B-Think
Active=32B, Total=32B
2026.05
75.8
ZAYA1-8B
Active=0.7B, Total=8B
2026.05
74.2
Arcee-Trinity-Mini
Active=3B, Total=26B
2026.05
70.6
Feedback
Search any
task
Search any
task