TemporalBench - FreshRetailNet T4: leaderboard
TemporalBench FreshRetailNet retail slice for T4 event-conditioned forecasting questions.
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | TimeSeries Scientist (deepseek-chat) | 56.82 | |
| 2 | TimeSeries Scientist (gpt-4o) | 56.82 | |
| 3 | TimeClaw (deepseek-v4-pro) | 43.94 | |
| 4 | AgentScope (deepseek-chat) | 42.42 | |
| 5 | TimeCopilot (deepseek-chat) | 38.1 | |
| 6 | MetaGPT (deepseek-chat) | 37.12 | |
| 7 | CAMEL (gpt-4o) | 31.06 | |
| 8 | CAMEL (deepseek-chat) | 29.55 | |
| 9 | Single LLM (deepseek-chat) | 26.52 | |
| 10 | AgentScope (gpt-4o) | 18.94 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench-freshretailnet-t4 · How It Works · Data refreshed daily, snapshot 2026-10-20.