DiagFlowBench - Termination Recognition: leaderboard
Metric: Termination recognition (%): share of terminal-node turns at which the model correctly halts the procedure (word-level Jaccard node matching), on 1,676 multi-turn maintenance conversations over 50 industrial diagnostic flowcharts from a consumer manufacturer, procedure graph given as JSON in the system prompt, temperature 0, via OpenRouter; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 235B A22B (Thinking) | 98.5 |
| 2 | Nemotron 3 Super | 86.1 |
| 3 | Llama 3.3 70B | 83.4 |
| 4 | GPT-OSS-120B | 74.4 |
| 5 | Llama 4 Maverick | 72.8 |
| 6 | Gemini 2.5 Flash | 71.8 |
| 7 | Qwen 3 30B A3B (Thinking) | 70.1 |
| 8 | Llama 4 Scout | 61.6 |
| 9 | GPT-4o Mini | 38.8 |
Interactive version: theaggregate.ai/benchmark?slug=diagflowbench-termination-recognition · How It Works · Data refreshed daily, snapshot 2026-09-29.