The New ChatGPT Playbook & Prompting Guide
Creator's benchmark testing how well AI models draw SVGs of Gary Busey, with timeline and LLM-judged leaderboard; GPT-5.6 models are top two.
BuseyBench at a glance
- What is BuseyBench?
- BuseyBench is a research. Informal benchmark that scores how well AI models draw SVG images of Gary Busey, ranked on an LLM-judged leaderboard.
- Does BuseyBench work in the EU?
- Unverified. No explicit evidence found. The scraped snippet about Claude Duet refers to a different product and is not relevant to BuseyBench. Last verified 14 Nov 2026.
- How much does BuseyBench cost?
- Pricing unknown.
- Where was BuseyBench shown?
- In 2 creator videos by Matt Wolfe. Most recently by Matt Wolfe on 15 Jul 2026, at 32:38 in “The New ChatGPT Playbook & Prompting Guide”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
BuseyBench (also written Busey Bench) is a creator-made benchmark that tests how well AI models generate SVG drawings of the actor Gary Busey. It was mentioned by Matt Wolfe in a video on ChatGPT prompting. It is a novelty test in the style of other informal SVG-drawing evaluations, not a standardized academic benchmark.
According to the creator's description, the benchmark includes a timeline of model outputs and a leaderboard where results are scored by an LLM judge. In the version referenced, GPT-5.6 models hold the top two positions. The provided material does not describe the prompts, scoring rubric, or the full list of models tested.
The benchmark appears to be hosted on or linked from Matt Wolfe's Future Tools site, which is a news and AI tools curation site. The scraped page text did not contain a dedicated BuseyBench page, so details such as exact URL, release date, license and methodology are unconfirmed.
Key features
- Tests SVG generation of Gary Busey across AI models
- LLM-judged scoring
- Leaderboard of model results
- Timeline view of model progress over time
2 moments
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
AI News: Fable's Back But This New Model is Better?
The creator's own benchmark, built with Fable, testing how well AI models draw SVGs of Gary Busey, with timeline, cost, token and duration views. It also has an image-generator section tracking evolution from Midjourney V1 to GPT Image 2.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
SP
SWE-bench Pro
Research
Benchmark from Scale AI testing AI agents on long-horizon software engineering tasks drawn from real codebases.
Available in EUResearch
5 Sept 2025Open source
PA
PaperBench
Research · OpenAI
OpenAI benchmark testing whether AI agents can replicate ICML 2024 papers from scratch, graded by hierarchical rubrics.
Available in EUResearch
2 Apr 2025Open source
AA
Artificial Analysis Intelligence Index v5
Research · Artificial Analysis
Artificial Analysis's aggregate benchmark index that scores language models on intelligence across multiple evaluations.
Available in EUResearch
Release date n/aFree
AL
Agents Last Exam
Research
Benchmark of AI agents on long-horizon professional workflows across 55 sub-industries, led by Berkeley RDI.
UnverifiedResearch
Release date n/a
CO
CORE-Bench
Research
Benchmark of 270 tasks testing whether AI agents can computationally reproduce results from scientific papers.
Available in EUResearch
Sept 2024Open source
RE
RealSWE
Research
Benchmark of frontier AI models on private, real-world enterprise codebases, published by Specific.
Available in EUResearch
Release date n/aFree