PlanBench-V - Scheme Evaluation: leaderboard
PlanBench-V (2026) tests vision-language models on interpreting Chinese and international spatial planning maps with questions curated by professional planners; answers receive scores from 0 to 2 against reference answers with annotated critical points, using objective checks or a GPT-4o-mini judge. This board is the mean score on judging the strengths and weaknesses of a planning proposal; higher is better.
Metric: Mean score (out of 2) on judging the strengths and weaknesses of a planning proposal, implementation level; answers to expert-curated questions on Chinese and international spatial planning maps are scored 0 to 2 by a GPT-4o-mini judge (temperature 0) against structured reference answers with annotated critical points; objective items use exact match or semantic similarity; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 30 Sep 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 Plus | 1.62 | #226 |
| 2 | GPT-5.4 | 1.59 | #128 |
| 3 | Kimi K2.6 | 1.44 | #181 |
| 4 | Gemini 2.5 Pro | 1.44 | #269 |
| 5 | Claude Opus 4.7 | 1.43 | #78 |
| 6 | GPT-4o | 1.22 | #744 |
| 7 | Qwen2.5-VL-72B-Instruct-AWQ | 1.15 | #706 |
| 8 | Qwen 3.6 Flash | 1.05 | #431 |
| 9 | InternVL3-9B | 0.921 | #1703 |
| 10 | Qwen 2 VL 7B | 0.857 | #2324 |
| 11 | Qwen 2.5 VL 7B Instruct | 0.802 | #1867 |
| 12 | InternVL3-14B | 0.709 | #1204 |
| 13 | Qwen 2.5 VL 3B Instruct | 0.697 | #2562 |
| 14 | Qwen2-VL-72B-Instruct-AWQ | 0.67 | |
| 15 | GPT-4o Mini | 0.636 | #1658 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=planbench-v-scheme-evaluation · How It Works · Data refreshed daily, snapshot 2026-11-16.