List your company

Forecast-based Reasoning on ODTQA-FoRe 1.0 (test)

36.31AccuracyTimeFore
11.225217.737624.2530.7624Jun 1, 2026

Evaluation results

MethodLinks
TimeForeModel=Qwen3 Next 80B2026.0636.3155.8661.2158.41
TimeForeModel=GLM4.5 Air2026.0635.4663.7358.9361.24
TimeForeModel=Qwen3 30B2026.0631.5961.7858.860.25
TimeForeModel=GPT OSS 120B2026.0631.3757.3547.3251.86
TimeForeModel=GPT OSS 20B2026.0627.853.6145.3149.11
VanillaModel=Qwen3 Next 80B2026.0624.4548.444.9646.62
VanillaModel=GLM4.5 Air2026.0623.5949.8247.6748.72
VanillaModel=GPT OSS 120B2026.0621.644.4438.1641.06
VanillaModel=GPT OSS 20B2026.0621.5246.7941.9844.25
VanillaModel=Qwen3 30B2026.0612.1929.0121.7624.87