TemporalBench — leaderboard
TemporalBench evaluates LLM-based agents on contextual and event-informed time-series tasks spanning multiple datasets and task types.
Metric: Overall MCQ Accuracy (%). Source: huggingface.co. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Single LLM (gpt-4o) | 34.11 |
| 2 | AgentScope (gpt-4o) | 32.91 |
| 3 | CAMEL (gpt-4o) | 32.33 |
| 4 | MetaGPT (gpt-4o) | 31.56 |
| 5 | TimeSeries Scientist (gpt-4o) | 23.96 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.