DiagChain: leaderboard

Metric: Correctly reconstructed reference steps (%; share of the 849 coverable reference steps of MAIN-69's 69 cases, pooled over the clean, noisy and raw evidence profiles; attack-chain reconstruction from heterogeneous telemetry with the ECRAG evidence-retrieval scaffold; a step counts when its evidence is observed, used, fully attributed and correctly ordered, with no earlier failure; temperature 0). Source: arxiv.org. Saturation forecast: Around December 2027. 6 models tracked.

Top models

#ModelScore
1GPT-5.539.58
2GLM-5.2 (High)28.15
3GLM-5.2 (Non-reasoning)25.32
4DeepSeek V4 Pro (Non-reasoning)20.26

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