List your company

Multi-task Language Understanding on MMLU Pro (Score)

82.6MMLU Pro ScoreQwen3-Next-80B-A3B-Think
70.1273.3676.679.84May 6, 2026

Evaluation results

MethodLinks
Qwen3-Next-80B-A3B-ThinkActive=3B, Total=80B2026.0582.6
Intellect-3Active=12B, Total=106B2026.0582.3
Mistral-Small-4-119BActive=6B, Total=119B2026.0581.6
Nemotron-3-Nano-30B-A3BActive=3B, Total=30B2026.0578.9
OLMo-3.1-32B-ThinkActive=32B, Total=32B2026.0575.8
ZAYA1-8BActive=0.7B, Total=8B2026.0574.2
Arcee-Trinity-MiniActive=3B, Total=26B2026.0570.6