BareBones - WTP-Bench (Full Color): 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 the full-colour sprite, the texture control for the silhouette board. Accuracy in percent; higher is better.

Metric: Exact-match accuracy (%) naming the Pokemon from its full-colour sprite (the texture control); 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

#ModelScoreOverall rank
1GPT-4.178.97#506
2Gemini 2.5 Pro78.19#280
3Gemini 2.5 Flash77.24#466
4Claude Sonnet 4.565.09#267
5GPT-4o Mini49.31#1680
6Grok 4 Fast46.9#446
7Claude Haiku 4.527.59#587
8Qwen 3 VL 4B13.36#1163
9InternVL2.5-26B4.14#2174
10LLaVA-OV-7B3.53#4498
11SmolVLM2.24
12LLaVA-v1.5-13B1.81#6941

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=barebones-wtp-bench-full-color · How It Works · Data refreshed daily, snapshot 2026-11-22.