LongRCA-Mini (All-at-Once): leaderboard
LongRCA Bench (2026) collects failed agent trajectories from five benchmarks, with the earliest decisive root-cause step annotated by humans; LongRCA-Mini is its fixed 200-trajectory sample, 40 per source. The model reads the whole execution log in one prompt and names the root-cause step; the score is the percentage of exact matches, macro-averaged over sources. Higher is better.
Metric: Root-step accuracy (%; exact match to the earliest decisive root-cause step; LongRCA-Mini, 200 fixed human-annotated failed agent trajectories, 40 from each of SWE-bench Pro, Terminal-Bench 2, TravelPlanner, VitaBench and WebArena Verified (macro-average of the five sources); All-at-once protocol: the whole execution log in one attribution prompt; invalid outputs count as errors). Source: arxiv.org. Saturation forecast: Around September 2028. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 17 | #30 |
| 2 | DeepSeek V4 Pro | 11.5 | #188 |
| 3 | Kimi K3 | 11 | #54 |
| 4 | DeepSeek V4 Flash | 7.5 | #258 |
| 5 | Qwen 3.5 35B A3B | 3.5 | #482 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=longrca-mini-all-at-once · How It Works · Data refreshed daily, snapshot 2026-11-13.