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

201–225 of 330 results
#2011542 rating ±44
GPT-5 Nano output

GPT-5 Nano

OpenAI / Aug 7, 2025 / openrouter

Busey likeness1.2
Face coherence5.4
Aesthetics4.3
Prompt adherence3.9

1 judged output · judge spread σ 0.30 · W 15 / L 19 / D 28

2.9overall
#2021486 rating ±44
Qwen3 Coder Plus output

Qwen3 Coder Plus

Qwen / Jul 22, 2025 / openrouter

Busey likeness1.5
Face coherence4.8
Aesthetics3.3
Prompt adherence4.7

1 judged output · judge spread σ 0.51 · W 12 / L 25 / D 25

2.9overall
#2031440 rating ±44
Qwen3 Coder 480B A35B output

Qwen3 Coder 480B A35B

Qwen / Jul 23, 2025 / openrouter

Busey likeness1.5
Face coherence4.3
Aesthetics4.3
Prompt adherence4.4

1 judged output · judge spread σ 0.59 · W 5 / L 25 / D 32

2.9overall
#2041397 rating ±43
Laguna S 2.1 output

Laguna S 2.1

Poolside / Jul 21, 2026 / openrouter

Busey likeness1.4
Face coherence4.0
Aesthetics3.9
Prompt adherence5.3

1 judged output · judge spread σ 0.56 · W 6 / L 31 / D 29

2.9overall
#2051341 rating ±45
Qwen3 235B A22B Instruct 2507 output

Qwen3 235B A22B Instruct 2507

Qwen / Jul 21, 2025 / openrouter

Busey likeness1.4
Face coherence4.5
Aesthetics3.5
Prompt adherence5.0

1 judged output · judge spread σ 0.42 · W 6 / L 38 / D 16

2.9overall
#2061743 rating ±41
Qwen3.5-27B output

Qwen3.5-27B

Qwen / Feb 25, 2026 / openrouter

Busey likeness1.7
Face coherence3.9
Aesthetics3.9
Prompt adherence4.0

1 judged output · judge spread σ 0.60 · W 40 / L 3 / D 29

2.8overall
#2071525 rating ±42
GPT-5.4 Nano output

GPT-5.4 Nano

OpenAI / Mar 17, 2026 / openrouter

Busey likeness1.4
Face coherence3.1
Aesthetics5.2
Prompt adherence4.6

1 judged output · judge spread σ 0.68 · W 19 / L 19 / D 32

2.8overall
#2081830 rating ±41
Nemotron 3 Super (free) output

Nemotron 3 Super (free)

NVIDIA / Mar 11, 2026 / openrouter

Busey likeness1.5
Face coherence3.8
Aesthetics3.7
Prompt adherence4.2

1 judged output · judge spread σ 0.43 · W 55 / L 3 / D 16

2.7overall
#2091804 rating ±39
Qwen3.5-Flash output

Qwen3.5-Flash

Qwen / Feb 25, 2026 / openrouter

Busey likeness1.0
Face coherence4.3
Aesthetics4.2
Prompt adherence4.3

1 judged output · judge spread σ 0.24 · W 59 / L 5 / D 16

2.7overall
#2101678 rating ±40
Palmyra X5 output

Palmyra X5

Writer / Apr 28, 2025 / openrouter

Busey likeness1.2
Face coherence4.6
Aesthetics3.4
Prompt adherence4.6

1 judged output · judge spread σ 0.27 · W 43 / L 12 / D 21

2.7overall
#2111585 rating ±41
DeepSeek V3 output

DeepSeek V3

DeepSeek / Dec 26, 2024 / openrouter

Busey likeness1.2
Face coherence5.1
Aesthetics3.3
Prompt adherence4.1

1 judged output · judge spread σ 0.33 · W 27 / L 14 / D 31

2.7overall
#2121475 rating ±41
Qwen3 30B A3B Thinking 2507 output

Qwen3 30B A3B Thinking 2507

Qwen / Jul 30, 2025 / openrouter

Busey likeness1.3
Face coherence4.7
Aesthetics3.6
Prompt adherence3.9

1 judged output · judge spread σ 0.40 · W 16 / L 23 / D 35

2.7overall
#2131437 rating ±40
gpt-oss-safeguard-20b output

gpt-oss-safeguard-20b

OpenAI / Oct 29, 2025 / openrouter

Busey likeness1.3
Face coherence4.5
Aesthetics3.4
Prompt adherence4.3

1 judged output · judge spread σ 0.55 · W 18 / L 32 / D 26

2.7overall
#2141170 rating ±40
Mistral Small 4 output

Mistral Small 4

Mistral / Mar 16, 2026 / openrouter

Busey likeness1.4
Face coherence4.1
Aesthetics3.9
Prompt adherence4.1

1 judged output · judge spread σ 0.48 · W 5 / L 61 / D 10

2.7overall
#2151659 rating ±37
GLM 4.7 Flash output

GLM 4.7 Flash

Z.ai / Jan 19, 2026 / openrouter

Busey likeness1.3
Face coherence4.4
Aesthetics3.1
Prompt adherence4.1

1 judged output · judge spread σ 0.44 · W 50 / L 7 / D 33

2.6overall
#2161640 rating ±38
Seed-2.0-Mini output

Seed-2.0-Mini

ByteDance Seed / Feb 14, 2026 / openrouter

Busey likeness1.0
Face coherence4.5
Aesthetics4.0
Prompt adherence3.9

1 judged output · judge spread σ 0.47 · W 47 / L 11 / D 28

2.6overall
#2171602 rating ±39
Laguna XS.2 output

Laguna XS.2

Poolside / Apr 28, 2026 / openrouter

Busey likeness1.3
Face coherence4.5
Aesthetics3.3
Prompt adherence4.0

1 judged output · judge spread σ 0.42 · W 34 / L 9 / D 37

2.6overall
#2181581 rating ±37
Kimi K2 Thinking output

Kimi K2 Thinking

MoonshotAI / Nov 6, 2025 / openrouter

Busey likeness1.2
Face coherence3.7
Aesthetics3.8
Prompt adherence4.7

1 judged output · judge spread σ 0.45 · W 41 / L 13 / D 34

2.6overall
#2191578 rating ±37
Gemini 2.5 Flash Lite output

Gemini 2.5 Flash Lite

Google / Jul 22, 2025 / openrouter

Busey likeness1.3
Face coherence3.8
Aesthetics3.9
Prompt adherence4.2

1 judged output · judge spread σ 0.46 · W 35 / L 10 / D 43

2.6overall
#2201558 rating ±38
Qwen Plus 0728 (thinking) output

Qwen Plus 0728 (thinking)

Qwen / Jul 28, 2025 / openrouter

Busey likeness1.2
Face coherence4.4
Aesthetics3.4
Prompt adherence4.1

1 judged output · judge spread σ 0.47 · W 31 / L 11 / D 44

2.6overall
#2211554 rating ±37
o3 Mini output

o3 Mini

OpenAI / Jan 31, 2025 / openrouter

Busey likeness1.1
Face coherence4.7
Aesthetics3.3
Prompt adherence4.3

1 judged output · judge spread σ 0.55 · W 32 / L 12 / D 44

2.6overall
#2221533 rating ±37
Gemma 3 27B output

Gemma 3 27B

Google / Mar 12, 2025 / openrouter

Busey likeness1.1
Face coherence4.7
Aesthetics3.1
Prompt adherence4.3

1 judged output · judge spread σ 0.60 · W 33 / L 15 / D 42

2.6overall
#2231531 rating ±36
Mercury 2 output

Mercury 2

Inception / Feb 24, 2026 / openrouter

Busey likeness0.8
Face coherence4.8
Aesthetics4.2
Prompt adherence3.9

1 judged output · judge spread σ 0.63 · W 35 / L 15 / D 42

2.6overall
#2241494 rating ±37
Mercury 2.5 Preview output

Mercury 2.5 Preview

Inception / Jun 26, 2025 / openrouter

Busey likeness2.0
Face coherence2.7
Aesthetics3.2
Prompt adherence4.1

1 judged output · judge spread σ 0.72 · W 26 / L 19 / D 43

2.6overall
#2251469 rating ±37
Nova 2 Lite output

Nova 2 Lite

Amazon / Dec 2, 2025 / openrouter

Busey likeness1.1
Face coherence4.4
Aesthetics2.9
Prompt adherence4.7

1 judged output · judge spread σ 0.55 · W 32 / L 27 / D 31

2.6overall
← PreviousPage 9 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