Creative Writing on WildBench (test)
64.4WildBench ScoreFull
Evaluation Results
| Method | Links | |
|---|---|---|
| FullModel=Qwen3, Ratio=0%, Zero-shot=true2026.03 | 64.4 | |
| FrequencyModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 63.2 | |
| EANModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 62.6 | |
| SEERModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 61.2 | |
| AIMERModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 60.4 | |
| REAPModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 56.8 | |
| EANModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 52.2 | |
| RandomModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 46.1 | |
| AIMERModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 41.3 | |
| REAPModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 22.6 | |
| MagnitudeModel=Qwen3, Ratio=25%, Zero-shot=true2026.03 | 11.9 | |
| RandomModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 2.7 | |
| SEERModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 1.8 | |
| FrequencyModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 1.5 | |
| MagnitudeModel=Qwen3, Ratio=50%, Zero-shot=true2026.03 | 0 |