TemporalBench - PSML T3: leaderboard
TemporalBench PSML process-systems slice for T3 temporal reasoning over system measurements.
Metric: Accuracy (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | TimeClaw (deepseek-v4-pro) | 36.4 | |
| 2 | Single LLM (deepseek-chat) | 34.8 | |
| 3 | Single LLM (gpt-4o) | 34.8 | |
| 4 | TimeCopilot (deepseek-v4-pro) | 34.8 | |
| 5 | TimeCopilot (deepseek-chat) | 28.8 | |
| 6 | MetaGPT (deepseek-chat) | 28 | |
| 7 | AgentScope (gpt-4o) | 27.2 | |
| 8 | CAMEL (deepseek-chat) | 25.2 | |
| 9 | AgentScope (deepseek-chat) | 24.8 | |
| 10 | TimeSeries Scientist (deepseek-chat) | 22.8 |
Interactive version: theaggregate.ai/benchmark?slug=temporalbench-psml-t3 · How It Works · Data refreshed daily, snapshot 2026-10-20.