TemporalBench - FreshRetailNet T3: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | TimeSeries Scientist (deepseek-chat) | 34.09 |
| 2 | TimeClaw (deepseek-v4-pro) | 21.02 |
| 3 | CAMEL (deepseek-chat) | 19.89 |
| 4 | Single LLM (deepseek-chat) | 16.85 |
| 5 | TimeCopilot (deepseek-chat) | 15.91 |
| 6 | AgentScope (gpt-4o) | 13.64 |
| 7 | TimeCopilot (deepseek-v4-pro) | 13.07 |
| 8 | CAMEL (gpt-4o) | 6.25 |
| 9 | AgentScope (deepseek-chat) | 5.68 |
| 10 | MetaGPT (deepseek-chat) | 5.11 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench-freshretailnet-t3 · How It Works · Data refreshed daily, snapshot 2026-09-05.