Cultural Reasoning on BLEnD (test)
85.81AccuracyC-Mining
Evaluation Results
| Method | Links | |
|---|---|---|
| C-MiningBackbone=Qwen3-32B, Instruction Tuning Method=C-Mining2026.04 | 85.81 | |
| Qwen3-32BBackbone=Qwen3-32B, Instruction Tuning Method=Standard2026.04 | 82.63 | |
| C-MiningBackbone=Qwen2.5-7B, Instruction Tuning Method=C-Mining2026.04 | 80.94 | |
| CultureSPABackbone=Qwen2.5-7B, Instruction Tuning Method=CultureSPA2026.04 | 78.69 | |
| Llama3.1-8BBackbone=Llama3.1-8B, Instruction Tuning Method=Standard2026.04 | 77.88 | |
| CultureBankBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureBank2026.04 | 77.75 | |
| Qwen2.5-7BBackbone=Qwen2.5-7B, Instruction Tuning Method=Standard2026.04 | 77.12 | |
| Ministral3-8BBackbone=Ministral3-8B, Instruction Tuning Method=Standard2026.04 | 76.52 | |
| CultureLLMBackbone=Qwen2.5-7B, Instruction Tuning Method=CultureLLM2026.04 | 74.75 | |
| GLM4-9BBackbone=GLM4-9B, Instruction Tuning Method=Standard2026.04 | 74.43 |