Society & Culture Understanding on Unified Korean Benchmark Society & Culture
82.2Ko-Sovereign (EM)Mi:dm K 2.5 Pro
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Mi:dm K 2.5 ProReasoning=On2026.03 | 82.2 | — | — | — | — | — | 92.8 | 82.83 | |
| K-EXAONE-236B-A23BReasoning=On2026.03 | 81.4 | — | — | — | — | — | 92.8 | 81.49 | |
| HyperCLOVAX-SEED-Think-32BReasoning=On2026.03 | 80.8 | — | — | — | — | — | 94.8 | 83.2 | |
| Qwen-3-30B-A3BReasoning=On2026.03 | 70.9 | — | — | — | — | — | 86 | 68.4 | |
| Solar-open-100BReasoning=On2026.03 | 64.9 | — | — | — | — | — | 90 | 77.7 | |
| K-EXAONE-236B-A23BReasoning=Off2026.03 | 64 | — | — | — | — | — | 84 | 79.9 | |
| Mi:dm K 2.5 ProReasoning=Off2026.03 | 63.6 | — | — | — | — | — | 87.6 | 81.3 | |
| HyperCLOVAX-SEED-Think-32BReasoning=Off2026.03 | 60 | — | — | — | — | — | 90 | 78.7 | |
| Qwen-3-30B-A3BReasoning=Off2026.03 | 49.3 | — | — | — | — | — | 82.4 | 66.6 | |
| Exaone-3.5-2.4B-instParameters=2.4B, Instruction-tuned=true2026.01 | — | 64 | 67.1 | 44.4 | 61.3 | 59.2 | — | — | |
| Exaone-3.5-7.8B-instParameters=7.8B, Instruction-tuned=true2026.01 | — | 71.6 | 69.3 | 46.9 | 72.9 | 65.2 | — | — | |
| Llama-3.1-8B-instParameters=8B, Instruction-tuned=true2026.01 | — | 43.2 | 36.4 | 33.8 | 49.5 | 40.7 | — | — | |
| Mi:dm 2.0 Base-instModel Size=Base, Instruction-tuned=true2026.01 | — | 89.6 | 86.4 | 56.3 | 81.5 | 78.4 | — | — | |
| Mi:dm 2.0 Mini-instModel Size=Mini, Instruction-tuned=true2026.01 | — | 66.4 | 61.4 | 36.7 | 70.8 | 58.8 | — | — | |
| Qwen3-14BParameters=14B2026.01 | — | 72.4 | 65.7 | 49.8 | 68.4 | 64.1 | — | — | |
| Qwen3-4BParameters=4B2026.01 | — | 53.6 | 42.9 | 35.8 | 50.6 | 45.7 | — | — |