TimeSage-MT - Analytical Quality: leaderboard

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 2028. 6 models tracked.

Top models

#ModelScore
1GPT-5.3 Codex35.14
2Gemini 3 Flash (Preview)31.1
3Qwen 3.5 122B A10B29.89
4GLM-5.129.48
5Claude Sonnet 4.628.75
6MiniMax-M2.727.87

Interactive version: theaggregate.ai/benchmark?slug=timesage-mt-analytical-quality · How It Works · Data refreshed daily, snapshot 2026-09-29.