TemporalBench - FreshRetailNet T2: leaderboard
TemporalBench FreshRetailNet retail slice for T2 event-informed forecasting questions.
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Single LLM (deepseek-chat) | 56.82 | |
| 2 | TimeSeries Scientist (deepseek-chat) | 56.82 | |
| 3 | TimeSeries Scientist (gpt-4o) | 56.82 | |
| 4 | Single LLM (gpt-4o) | 52.27 | |
| 5 | MetaGPT (deepseek-chat) | 41.67 | |
| 6 | AgentScope (deepseek-chat) | 34.85 | |
| 7 | TimeClaw (deepseek-v4-pro) | 31.06 | |
| 8 | TimeCopilot (deepseek-v4-pro) | 23.81 | |
| 9 | TimeCopilot (deepseek-chat) | 20.29 | |
| 10 | AgentScope (gpt-4o) | 12.12 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench-freshretailnet-t2 · How It Works · Data refreshed daily, snapshot 2026-10-20.