Skip to main content
BuseyBenchcreative model benchmarkSVG models tested
SVG testImage testLeaderboardTimelineMethodology
Browse
SVG testImage testLeaderboardTimelineMethodology
BuseyBenchSame prompt. Same rules. Maximum facial voltage.
Score trendsTimelineMethodologyAboutPrivacyGovernanceRSSAdmin
330 SVG models tested
BuseyBench SVG TestImage Generator Portrait Test

Leaderboard

Judged. Ranked. Busey'd.

One output per model, independent judge scores, and close-score pairwise tie-breaks. The best Gary Busey portraits rise to the top.

Explore the dataDrawing ability over time→
330 models ranked8901 official head-to-head verdictsPairwise tie-break active

Official standings

The rankings

151–175 of 330 results
#1511264 rating ±42
Inkling Small output

Inkling Small

Thinking Machines / Jul 30, 2026 / openrouter

Busey likeness2.2
Face coherence5.1
Aesthetics4.2
Prompt adherence6.2

1 judged output · judge spread σ 0.37 · W 4 / L 55 / D 9

3.7overall
#1521973 rating ±44
Grok 4.20 Multi-Agent output

Grok 4.20 Multi-Agent

xAI / Mar 10, 2026 / openrouter

Busey likeness1.8
Face coherence5.3
Aesthetics4.7
Prompt adherence6.1

1 judged output · judge spread σ 0.76 · W 49 / L 0 / D 15

3.6overall
#1531790 rating ±44
GPT-4.1 output

GPT-4.1

OpenAI / Apr 14, 2025 / openrouter

Busey likeness1.9
Face coherence5.4
Aesthetics4.8
Prompt adherence5.6

1 judged output · judge spread σ 0.61 · W 33 / L 4 / D 25

3.6overall
#1541751 rating ±44
Grok Build 0.1 output

Grok Build 0.1

xAI / May 20, 2026 / openrouter

Busey likeness1.8
Face coherence5.9
Aesthetics4.4
Prompt adherence5.6

1 judged output · judge spread σ 0.75 · W 30 / L 5 / D 29

3.6overall
#1551747 rating ±42
Claude Sonnet 4.5 output

Claude Sonnet 4.5

Anthropic / Sep 29, 2025 / openrouter

Busey likeness2.2
Face coherence5.1
Aesthetics4.3
Prompt adherence5.8

1 judged output · judge spread σ 0.65 · W 34 / L 10 / D 24

3.6overall
#1561690 rating ±41
Kimi K2.5 output

Kimi K2.5

MoonshotAI / Jan 27, 2026 / openrouter

Busey likeness1.7
Face coherence6.2
Aesthetics5.1
Prompt adherence5.2

1 judged output · judge spread σ 0.61 · W 26 / L 11 / D 35

3.6overall
#1571461 rating ±41
Mistral Medium 3.1 output

Mistral Medium 3.1

Mistral / Aug 13, 2025 / openrouter

Busey likeness2.8
Face coherence4.2
Aesthetics3.9
Prompt adherence5.6

1 judged output · judge spread σ 0.62 · W 13 / L 37 / D 22

3.6overall
#1581378 rating ±43
GPT-4o (2024-11-20) output

GPT-4o (2024-11-20)

OpenAI / Nov 20, 2024 / openrouter

Busey likeness2.5
Face coherence5.2
Aesthetics3.0
Prompt adherence5.4

1 judged output · judge spread σ 0.28 · W 7 / L 39 / D 20

3.6overall
#1591333 rating ±44
GPT-5.4 Mini output

GPT-5.4 Mini

OpenAI / Mar 17, 2026 / openrouter

Busey likeness1.5
Face coherence6.1
Aesthetics5.3
Prompt adherence5.7

1 judged output · judge spread σ 0.38 · W 2 / L 38 / D 24

3.6overall
#1601772 rating ±44
o4 Mini High output

o4 Mini High

OpenAI / Apr 16, 2025 / openrouter

Busey likeness2.4
Face coherence4.7
Aesthetics3.9
Prompt adherence5.3

1 judged output · judge spread σ 0.70 · W 33 / L 5 / D 26

3.5overall
#1611620 rating ±44
Inkling output

Inkling

Thinking Machines / Jul 2, 2026 / direct api

Busey likeness2.5
Face coherence4.2
Aesthetics4.1
Prompt adherence5.3

1 judged output · judge spread σ 0.50 · W 21 / L 15 / D 28

3.5overall
#1621572 rating ±43
Nex-N2-Mini output

Nex-N2-Mini

Nex AGI / Jun 2, 2026 / openrouter

Busey likeness1.7
Face coherence4.6
Aesthetics5.7
Prompt adherence6.1

1 judged output · judge spread σ 0.46 · W 17 / L 20 / D 29

3.5overall
#1631553 rating ±43
Kimi K2 0711 output

Kimi K2 0711

MoonshotAI / Jul 11, 2025 / openrouter

Busey likeness1.7
Face coherence5.9
Aesthetics4.6
Prompt adherence5.6

1 judged output · judge spread σ 0.50 · W 17 / L 23 / D 26

3.5overall
#1641394 rating ±43
Ling-3.0-flash output

Ling-3.0-flash

inclusionAI / Jul 23, 2026 / openrouter

Busey likeness1.7
Face coherence5.7
Aesthetics4.6
Prompt adherence5.8

1 judged output · judge spread σ 0.64 · W 8 / L 38 / D 20

3.5overall
#1651371 rating ±43
GPT-5.1 output

GPT-5.1

OpenAI / Nov 13, 2025 / openrouter

Busey likeness2.4
Face coherence3.8
Aesthetics6.0
Prompt adherence4.0

1 judged output · judge spread σ 0.75 · W 2 / L 35 / D 29

3.5overall
#1661905 rating ±44
KAT-Coder-Pro V2 output

KAT-Coder-Pro V2

Kwaipilot / Mar 27, 2026 / openrouter

Busey likeness1.9
Face coherence5.2
Aesthetics4.2
Prompt adherence5.2

1 judged output · judge spread σ 0.72 · W 48 / L 3 / D 13

3.4overall
#1671649 rating ±42
Gemma 4 26B A4B output

Gemma 4 26B A4B

Google / Apr 2, 2026 / openrouter

Busey likeness1.7
Face coherence5.5
Aesthetics4.4
Prompt adherence5.5

1 judged output · judge spread σ 0.80 · W 27 / L 15 / D 26

3.4overall
#1681600 rating ±44
Qwen3.6 35B A3B output

Qwen3.6 35B A3B

Qwen / Apr 16, 2026 / openrouter

Busey likeness1.6
Face coherence4.7
Aesthetics5.2
Prompt adherence5.9

1 judged output · judge spread σ 0.65 · W 23 / L 18 / D 23

3.4overall
#1691486 rating ±44
DeepSeek V4 Pro 0813 output

DeepSeek V4 Pro 0813

DeepSeek / Aug 12, 2026 / openrouter

Busey likeness1.5
Face coherence5.2
Aesthetics5.4
Prompt adherence5.3

1 judged output · judge spread σ 0.54 · W 11 / L 25 / D 26

3.4overall
#1701341 rating ±44
GPT-4o Search Preview output

GPT-4o Search Preview

OpenAI / Mar 12, 2025 / openrouter

Busey likeness2.3
Face coherence5.4
Aesthetics3.3
Prompt adherence4.6

1 judged output · judge spread σ 0.54 · W 6 / L 42 / D 16

3.4overall
#1711279 rating ±44
Ring-2.6-1T output

Ring-2.6-1T

inclusionAI / May 8, 2026 / openrouter

Busey likeness1.4
Face coherence5.8
Aesthetics5.0
Prompt adherence5.4

1 judged output · judge spread σ 0.14 · W 3 / L 44 / D 15

3.4overall
#1721938 rating ±43
Qwen3.5-35B-A3B output

Qwen3.5-35B-A3B

Qwen / Feb 25, 2026 / openrouter

Busey likeness1.8
Face coherence5.4
Aesthetics4.2
Prompt adherence4.7

1 judged output · judge spread σ 0.64 · W 53 / L 3 / D 10

3.3overall
#1731687 rating ±43
Qwen3.6 Max Preview output

Qwen3.6 Max Preview

Qwen / Apr 20, 2026 / openrouter

Busey likeness1.9
Face coherence3.7
Aesthetics4.9
Prompt adherence6.0

1 judged output · judge spread σ 0.52 · W 31 / L 12 / D 23

3.3overall
#1741671 rating ±44
Gemini 3.1 Flash Lite Preview output

Gemini 3.1 Flash Lite Preview

Google / Mar 3, 2026 / openrouter

Busey likeness1.7
Face coherence5.2
Aesthetics3.4
Prompt adherence5.6

1 judged output · judge spread σ 0.77 · W 28 / L 13 / D 23

3.3overall
#1751603 rating ±43
GPT-5 Codex output

GPT-5 Codex

OpenAI / Sep 15, 2025 / openrouter

Busey likeness2.0
Face coherence3.9
Aesthetics4.6
Prompt adherence5.6

1 judged output · judge spread σ 0.50 · W 17 / L 14 / D 35

3.3overall
← PreviousPage 7 of 14Next →
Ranking statusDisplayed score + pairwise tie-break

Overall = likeness 50% + face 20% + aesthetics 15% + prompt 15%. Each model contributes one canonical judged output. The visible overall score, rounded to one decimal, always sets the score band. Pairwise results only order models tied within that displayed band, so a lower displayed score can never leapfrog a higher one.

Read the full methodology →View score trends →
1canonical output judged per model
Closest-scorepairwise matchmaking strategy
busey-v2current scoring rubric