Forecast-based Reasoning on ODTQA-FoRe 1.0 (test)
36.31AccuracyTimeFore
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TimeForeModel=Qwen3 Next 80B2026.06 | 36.31 | 55.86 | 61.21 | 58.41 | |
| TimeForeModel=GLM4.5 Air2026.06 | 35.46 | 63.73 | 58.93 | 61.24 | |
| TimeForeModel=Qwen3 30B2026.06 | 31.59 | 61.78 | 58.8 | 60.25 | |
| TimeForeModel=GPT OSS 120B2026.06 | 31.37 | 57.35 | 47.32 | 51.86 | |
| TimeForeModel=GPT OSS 20B2026.06 | 27.8 | 53.61 | 45.31 | 49.11 | |
| VanillaModel=Qwen3 Next 80B2026.06 | 24.45 | 48.4 | 44.96 | 46.62 | |
| VanillaModel=GLM4.5 Air2026.06 | 23.59 | 49.82 | 47.67 | 48.72 | |
| VanillaModel=GPT OSS 120B2026.06 | 21.6 | 44.44 | 38.16 | 41.06 | |
| VanillaModel=GPT OSS 20B2026.06 | 21.52 | 46.79 | 41.98 | 44.25 | |
| VanillaModel=Qwen3 30B2026.06 | 12.19 | 29.01 | 21.76 | 24.87 |