List your company

Multitask Language Understanding on MMLU Redux

84.13AccuracyT2T
2.188423.461744.73566.0083Jun 11, 2026

Evaluation results

MethodLinks
T2TPair=8B → 14B, Regime=context-aware2026.0684.1367.08
T2TPair=14B → 8B, Regime=context-aware2026.0683.4355.5
T2TPair=4B → 14B, Regime=context-aware2026.0682.8756.24
T2TPair=4B → 8B, Regime=context-aware2026.0680.7537.73
T2TPair=14B → 4B, Regime=context-aware2026.0680.6143.48
T2TPair=8B → 4B, Regime=context-aware2026.0679.3933.91
dense alignmentPair=4B → 14B, Regime=context-aware2026.0678.5721.54
dense alignmentPair=4B → 8B, Regime=context-aware2026.0678.5212.56
dense alignmentPair=14B → 8B, Regime=context-aware2026.0678.0415.64
dense alignmentPair=8B → 4B, Regime=context-aware2026.0677.867.95
dense alignmentPair=14B → 4B, Regime=context-aware2026.0677.6610.18
dense alignmentPair=8B → 14B, Regime=context-aware2026.0677.3821.79
Ours-context-unawarePair=8B → 4B, Context Setting=context-unaware2026.0677.066.56
C2CPair=14B → 8B, Regime=context-aware2026.0675.997.83
C2CPair=4B → 8B, Regime=context-aware2026.0675.874.5
Ours-context-unawarePair=4B → 8B, Context Setting=context-unaware2026.0674.599.42
C2CPair=8B → 14B, Regime=context-aware2026.0673.817.42
C2CPair=4B → 14B, Regime=context-aware2026.0672.766.64
Receiver-onlyPair=4B → 8B, Regime=context-aware2026.0672.119.85
Receiver-onlyPair=14B → 8B, Regime=context-aware2026.0672.119.85
Receiver-onlyPair=4B → 14B, Regime=context-aware2026.0671.831.16
Receiver-onlyPair=8B → 14B, Regime=context-aware2026.0671.831.16
C2CPair=8B → 4B, Regime=context-aware2026.0670.193.43
C2CPair=14B → 4B, Regime=context-aware2026.0669.735.01
Ours-context-unawarePair=14B → 8B, Context Setting=context-unaware2026.0667.8413.28
Ours-context-unawarePair=14B → 4B, Context Setting=context-unaware2026.0667.158.9
Receiver-onlyPair=8B → 4B, Regime=context-aware2026.06659.18
Receiver-onlyPair=14B → 4B, Regime=context-aware2026.06659.18
Ours-context-unawarePair=4B → 14B, Context Setting=context-unaware2026.0662.8617.15
Ours-context-unawarePair=8B → 14B, Context Setting=context-unaware2026.0654.9215.85
T2T-context-unawarePair=8B → 4B, Context Setting=context-unaware2026.0625.1832.75
T2T-context-unawarePair=14B → 4B, Context Setting=context-unaware2026.0624.5241.95
T2T-context-unawarePair=4B → 14B, Context Setting=context-unaware2026.0623.0660.83
T2T-context-unawarePair=8B → 14B, Context Setting=context-unaware2026.0622.872.06
C2C-context-unawarePair=4B → 8B, Context Setting=context-unaware2026.0621.9114.94
T2T-context-unawarePair=14B → 8B, Context Setting=context-unaware2026.0621.4153.8
T2T-context-unawarePair=4B → 8B, Context Setting=context-unaware2026.062137.86
C2C-context-unawarePair=4B → 14B, Context Setting=context-unaware2026.0610.2620.05
C2C-context-unawarePair=8B → 4B, Context Setting=context-unaware2026.068.214.76
C2C-context-unawarePair=8B → 14B, Context Setting=context-unaware2026.067.149.84
C2C-context-unawarePair=14B → 4B, Context Setting=context-unaware2026.066.1117.93
C2C-context-unawarePair=14B → 8B, Context Setting=context-unaware2026.065.3424.77