BareBones - WTP-Bench (Silhouette): leaderboard
BareBones (2026) tests zero-shot recognition from shape; its WTP-Bench set asks vision-language models to name each of 1,160 Pokemon from its sprite, scored as an exact species-and-form match of the top-1 answer. This board shows only the binarized silhouette, with no colour, texture or background. Accuracy in percent; higher is better.
Metric: Exact-match accuracy (%) naming the Pokemon from its pure-shape silhouette (no colour, texture or background); 1,160 Pokemon sprites, exact species-and-form match of the model's top-1 name (Master Ball tier), zero-shot, temperature 0 for API models and a 100-token output cap for open-weight models; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 53.1 | #261 |
| 2 | GPT-4.1 | 49.48 | #505 |
| 3 | Gemini 2.5 Flash | 30 | #463 |
| 4 | Claude Haiku 4.5 | 27.41 | #583 |
| 5 | Gemini 2.5 Pro | 23.02 | #276 |
| 6 | GPT-4o Mini | 8.53 | #1667 |
| 7 | Grok 4 Fast | 7.93 | #447 |
| 8 | Qwen 3 VL 4B | 3.1 | #1151 |
| 9 | LLaVA-OV-7B | 1.81 | #4475 |
| 10 | InternVL2.5-26B | 1.72 | #2156 |
| 11 | SmolVLM | 0.95 | |
| 12 | LLaVA-v1.5-13B | 0.69 | #6926 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=barebones-wtp-bench-silhouette · How It Works · Data refreshed daily, snapshot 2026-11-21.