TimeSage-MT - L2 Multi-Skill Analysis: leaderboard

Metric: Outcome score (%) on the 60 L2 multi-skill analysis tasks (5-12 turns, 2-4 dependent analytical steps): 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 2029. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.638.3
2GLM-5.137.5
3GPT-5.3 Codex34.96
4Qwen 3.5 122B A10B33.63
5MiniMax-M2.733.42
6Gemini 3 Flash (Preview)31.74

Interactive version: theaggregate.ai/benchmark?slug=timesage-mt-l2-multi-skill-analysis · How It Works · Data refreshed daily, snapshot 2026-09-29.