ARFBench - Categorization: leaderboard
Time series question answering on software incident data in ARFBench (2026, Datadog): multiple-choice questions over multivariate production telemetry from real incidents, with the series shown as chart images. Accuracy on the Categorization questions (which type of anomaly occurs, such as a level shift or transient spike), in percent; higher is better.
Metric: Accuracy (%) on the 104 Categorization questions (level shift, transient spike, seasonality, variance or trend change) of ARFBench, for the time series rendered as chart images (Matplotlib plots, three images for paired questions), with the series description and channel names as text; few-shot multiple-choice prompting with shuffled answer choices, temperature 0.05 (default for models without the setting), reasoning models at medium effort with 2,000 output tokens, blank or invalid answers counted wrong; higher is better. Source: arxiv.org. Saturation forecast: Around December 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Toto-1.0-QA-Experimental 32B (TSFM-VLM) | 66.3 | ||
| 2 | Claude Opus 4.6 | 63.5 | #113 | |
| 3 | GPT-5 | 59.6 | #178 | |
| 4 | GPT-4.1 | 56.7 | #505 | |
| 5 | GPT-5.4 | Medium | 56.7 | #135 |
| 6 | Gemini 3 Pro | 54.8 | #145 | |
| 7 | Claude Sonnet 4.5 | 53.8 | #261 | |
| 8 | Qwen 3 VL 32B (post-trained) | 52.9 | ||
| 9 | GPT-4o | 51.9 | #751 | |
| 10 | Qwen 3 VL 32B | 50 | #622 | |
| 11 | Qwen 3 VL 8B | 45.2 | #917 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=arfbench-categorization · How It Works · Data refreshed daily, snapshot 2026-11-21.