S2SServiceBench (Decision Analysis and Planning): leaderboard
Metric: Level 3 overall score (0-1 printed, shown times 100): unweighted mean over the ten service products (161 expert-selected cases in all) of a schema-constrained strategic assessment and planning report, graded 0-5 on six rubric dimensions by a GPT-5.2 judge and printed on a 0-1 scale; direct prompting with the product artifacts, one response per task; GPT-5.2 is also a subject; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 50.88 | #105 |
| 2 | Claude Opus 4.5 | 41.81 | #79 |
| 3 | Gemini 3 Pro | 32.68 | #77 |
| 4 | Qwen 3 VL 32B Instruct | 31.42 | #276 |
| 5 | Grok 4 | 31.34 | #169 |
| 6 | Llama 4 Maverick Instruct | 20.16 | #439 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=s2sservicebench-decision-analysis-and-planning · How It Works · Data refreshed daily, snapshot 2026-10-11.