Fuel level estimation on GPQA Diamond
13.22rMAEFuel Gauge
Evaluation Results
| Method | Links | |
|---|---|---|
| Fuel GaugeModel=Qwen3-8B2026.03 | 13.22 | |
| Fuel GaugeModel=Qwen3-4B2026.03 | 15.88 | |
| MeanModel=Qwen3-8B2026.03 | 25.01 | |
| MedianModel=Qwen3-8B2026.03 | 27.43 | |
| MeanModel=Qwen3-4B2026.03 | 28.6 | |
| MedianModel=Qwen3-4B2026.03 | 31.61 | |
| EoC ProbModel=Qwen3-4B2026.03 | 49.99 | |
| EoC ProbModel=Qwen3-8B2026.03 | 49.99 |