TemporalBench - FreshRetailNet T1: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | AgentScope (deepseek-chat) | 70.45 |
| 2 | MetaGPT (deepseek-chat) | 69.89 |
| 3 | Single LLM (deepseek-chat) | 68.18 |
| 4 | CAMEL (deepseek-chat) | 67.05 |
| 5 | CAMEL (gpt-4o) | 64.2 |
| 6 | Single LLM (gpt-4o) | 63.64 |
| 7 | AgentScope (gpt-4o) | 62.5 |
| 8 | MetaGPT (gpt-4o) | 62.5 |
| 9 | TimeCopilot (deepseek-v4-pro) | 59.09 |
| 10 | TimeClaw (deepseek-v4-pro) | 56.25 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench-freshretailnet-t1 · How It Works · Data refreshed daily, snapshot 2026-09-05.