PerspectiveGap - Prompt Writing: leaderboard
Measures whether a model can compose role-specific prompts for a multi-agent orchestration without over-sharing context. Each of 110 scenarios supplies a role list, a shuffled set of information fragments and one injected distractor, against a reference assignment giving each role exactly the fragments it needs. Free-form prompt writing asks for the final sub-agent prompts, exposing models that can identify the boundary as a set of identifiers yet fail to preserve it when writing natural-language instructions. A deterministic rule-only scorer audits containment with phrase-level fingerprints; strict pass is all-or-nothing, scoring 1 only when an evaluation omits no required fragment and includes nothing out of role. This series reports PerspectiveGap - Prompt Writing using Pass Rate (%).
Metric: Pass Rate (%). Source: huggingface.co. Saturation forecast: Around November 2027. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 68.6 | #33 |
| 2 | GPT-5.6 Sol | 49.1 | #22 |
| 3 | GPT-5.6 Terra | 41.8 | #40 |
| 4 | Grok 4.6 | 38.6 | #29 |
| 5 | DeepSeek V4 Pro | 26.8 | #112 |
| 6 | Claude Sonnet 4.6 | 25.5 | #94 |
| 7 | Kimi K2.6 | 25 | #113 |
| 8 | DeepSeek V4 Flash | 25 | #155 |
| 9 | Claude Fable 5 | 24.1 | #20 |
| 10 | Gemini 3.1 Pro (Preview) | 23.6 | #64 |
| 11 | GPT-5.6 Luna | 19.1 | #79 |
| 12 | Kimi K2.5 | 16.8 | #152 |
| 13 | Claude Sonnet 5 | 16.4 | #65 |
| 14 | MiMo-V2.5-Pro | 15 | #167 |
| 15 | GLM-5 | 14.5 | #149 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=perspectivegap-prompt-writing · How It Works · Data refreshed daily, snapshot 2026-11-05.