TimeSage-MT - Analytical Quality: leaderboard
TimeSage-MT (2026) evaluates LLM agents in multi-turn time-series analysis dialogues with verifiable, code-derived answers, here under its Code-Enabled Reasoning setting in which the model writes Python that a sandbox executes. This board is the analytical quality dimension, a GPT-5.4 judge score in percent for correctness, depth and soundness of the analysis against the actual data; higher is better.
Metric: Analytical quality (%): GPT-5.4 judge score for correctness, depth and conclusion soundness against the actual data and reference output, averaged over the applicable tasks; Code-Enabled Reasoning setting (the model writes Python, a sandbox runs it, the model answers from stdout; 240 multi-turn time-series analysis tasks over 8 domains), temperature 0, reasoning effort high where supported and medium for GPT-5.3-Codex; higher is better. Source: arxiv.org. Saturation forecast: Around March 2028. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.3 Codex | 35.14 | #116 |
| 2 | Gemini 3 Flash (Preview) | 31.1 | #144 |
| 3 | Qwen 3.5 122B A10B | 29.89 | #331 |
| 4 | GLM-5.1 | 29.48 | #179 |
| 5 | Claude Sonnet 4.6 | 28.75 | #161 |
| 6 | MiniMax-M2.7 | 27.87 | #518 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=timesage-mt-analytical-quality · How It Works · Data refreshed daily, snapshot 2026-11-13.