TimeSage-MT - L1 Open Exploration: leaderboard

Metric: Outcome score (%) on the 60 L1 open-exploration tasks (3-10 turns, profile or data-summary answers): per-task mean of the applicable outcome dimensions (numerical accuracy, factual verification, GPT-5.4-judged analytical quality and code correctness, plus decision making at L4); 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 May 2028. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.649.61
2GLM-5.149.11
3GPT-5.3 Codex48.86
4Qwen 3.5 122B A10B47.18
5MiniMax-M2.745.29
6Gemini 3 Flash (Preview)44.08

Interactive version: theaggregate.ai/benchmark?slug=timesage-mt-l1-open-exploration · How It Works · Data refreshed daily, snapshot 2026-09-29.