Cultural Reasoning on SAGE (test)
97.57AccuracyC-Mining
Evaluation Results
| Method | Links | |
|---|---|---|
| C-MiningBackbone=Qwen3-32B, Instruction Tuning Method=C-Mining2026.04 | 97.57 | |
| C-MiningBackbone=Qwen2.5-7B, Instruction Tuning Method=C-Mining2026.04 | 96.59 | |
| CultureBankBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureBank2026.04 | 96.23 | |
| Qwen3-32BBackbone=Qwen3-32B, Instruction Tuning Method=Standard2026.04 | 95.01 | |
| Qwen2.5-7BBackbone=Qwen2.5-7B, Instruction Tuning Method=Standard2026.04 | 93.19 | |
| CultureSPABackbone=Qwen2.5-7B, Instruction Tuning Method=CultureSPA2026.04 | 92.46 | |
| CultureLLMBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureLLM2026.04 | 90.02 | |
| Llama3.1-8BBackbone=Llama3.1-8B, Instruction Tuning Method=Standard2026.04 | 89.66 | |
| GLM4-9BBackbone=GLM4-9B, Instruction Tuning Method=Standard2026.04 | 86.98 | |
| Ministral3-8BBackbone=Ministral3-8B, Instruction Tuning Method=Standard2026.04 | 79.81 |