List your company

General Knowledge Question Answering on MMLU 1000

48Pass@1Agentica-24k
34.4837.9941.545.01Nov 28, 2025

Evaluation results

MethodLinks
Agentica-24kTraining Regime=Base Model2025.11489340.76
Agentica-24k + SLPO (Direct)Training Regime=SLPO (Direct)2025.11483901.82
ORION-AG-SLPOTraining Regime=SLPO, Base Model=Agentica-24k2025.11482822.52
ORION-AG-GRPOTraining Regime=GRPO, Base Model=Agentica-24k2025.11471574.52
ORION-DS-GRPOTraining Regime=GRPO, Base Model=DeepSeek R1 1.5b2025.11461664.28
L1 MaxTraining Regime=Baseline2025.11452882.46
DeepSeek R1 1.5bTraining Regime=Base Model2025.11457101
DeepSeek R1 1.5b + SLPO (Direct)Training Regime=SLPO (Direct)2025.11454901.45
ORION-DS-SLPOTraining Regime=SLPO, Base Model=DeepSeek R1 1.5b2025.11434914.49
ORION-DSTraining Regime=Mentalese SFT, Base Model=DeepSeek R1 1.5b2025.11356710.6
ORION-AGTraining Regime=Mentalese SFT, Base Model=Agentica-24k2025.11356211.45