Atlas

Benchmarks

← All benchmarks

BuseyBench SVG

Multimodal · 2026-07-02

BuseyBench SVG measures how well a model creates a standalone 1024×1024 SVG portrait of Gary Busey from one fixed no-web prompt. Three vision judges each score the rendered output three times; BuseyBench takes each judge's median and then averages the judges. Its raw 0–10 score combines Busey likeness (50%), face coherence (20%), visual aesthetics (15%), and prompt adherence (15%); Atlas stores this raw absolute score rather than the leaderboard's pairwise-adjusted ranking score.

Top models (higher is better)

ModelScore
GPT-6.1 Sol8.0
Gemini 4 Argon7.6
GPT-6 Sol7.5
GPT-6 Astra7.3
GPT-6 Sol Pro7.2
GPT-6.1 Sol Pro7.1
Claude Fable 5.17.0
Claude Opus 5.56.8
Gemini 3.7 Flash6.6
Gemini 3.8 Flash6.6
Muse Wonder6.6
Claude Sonnet 5.56.5
GPT-5.6 Terra Pro6.5
GPT-6 Luna6.4
GPT-6 Luna Pro6.3
GPT-5.6 Sol Pro6.3
Claude Opus 56.3
Gemini 3.1 Pro Preview6.3
GLM-5.36.2
Kimi K36.2
GPT-5.6 Sol6.1
GPT-5.6 Terra6.1
GPT-5.5 Pro6.1
GPT-5.56.0
MiMo-V2.6-Pro6.0
Gemini 3.5 Flash5.9
Claude Fable 55.9
Fugu Ultra v1.05.8
Ember-15.8
Mistral Large 4 Preview5.8
Qwen3.8 Max (0902)5.8
Qwen3.8 27B5.8
GPT-5.6 Luna Pro5.7
Muse Spark 1.35.7
Muse Spark 1.25.6
Nex-N2.5-Pro5.6
Qwen3.8 Flash5.6
GLM-5.3 Flash5.5
Opus 4.65.5
GPT-5.2 Pro5.5
Loading Atlas data…