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

126–150 of 330 results
#1261244 rating ±49
Seed-2.0-Lite output

Seed-2.0-Lite

ByteDance Seed / Mar 10, 2026 / openrouter

Busey likeness2.4
Face coherence5.7
Aesthetics5.1
Prompt adherence6.6

1 judged output · judge spread σ 0.29 · W 0 / L 45 / D 7

4.1overall
#1272236 rating ±44
Switchpoint Router output

Switchpoint Router

Switchpoint / Jul 11, 2025 / openrouter

Busey likeness2.9
Face coherence4.9
Aesthetics4.1
Prompt adherence6.6

1 judged output · judge spread σ 0.80 · W 55 / L 0 / D 7

4.0overall
#1281767 rating ±44
GLM 4.7 output

GLM 4.7

Z.ai / Dec 22, 2025 / openrouter

Busey likeness2.6
Face coherence5.5
Aesthetics4.8
Prompt adherence5.8

1 judged output · judge spread σ 1.21 · W 24 / L 15 / D 25

4.0overall
#1291761 rating ±44
o3 Pro output

o3 Pro

OpenAI / Jun 10, 2025 / openrouter

Busey likeness2.6
Face coherence5.0
Aesthetics4.9
Prompt adherence6.4

1 judged output · judge spread σ 0.64 · W 23 / L 15 / D 26

4.0overall
#1301619 rating ±44
KAT-Coder-Air V2.5 output

KAT-Coder-Air V2.5

Kwaipilot / Jul 10, 2026 / openrouter

Busey likeness2.4
Face coherence5.0
Aesthetics5.4
Prompt adherence6.3

1 judged output · judge spread σ 1.04 · W 14 / L 26 / D 22

4.0overall
#1311616 rating ±46
Qwen3.6 Flash output

Qwen3.6 Flash

Qwen / Apr 27, 2026 / openrouter

Busey likeness2.2
Face coherence5.7
Aesthetics5.4
Prompt adherence6.7

1 judged output · judge spread σ 0.69 · W 8 / L 23 / D 27

4.0overall
#1321609 rating ±46
o1-pro output

o1-pro

OpenAI / Mar 19, 2025 / openrouter

Busey likeness3.0
Face coherence5.2
Aesthetics3.9
Prompt adherence6.0

1 judged output · judge spread σ 0.27 · W 11 / L 27 / D 20

4.0overall
#1331548 rating ±46
MiniMax M2 output

MiniMax M2

MiniMax / Oct 23, 2025 / openrouter

Busey likeness2.3
Face coherence6.1
Aesthetics5.2
Prompt adherence6.0

1 judged output · judge spread σ 0.96 · W 5 / L 29 / D 24

4.0overall
#1341889 rating ±44
Gemini 2.5 Pro Preview 06-05 output

Gemini 2.5 Pro Preview 06-05

Google / Jun 5, 2025 / openrouter

Busey likeness2.5
Face coherence5.2
Aesthetics4.7
Prompt adherence6.2

1 judged output · judge spread σ 0.84 · W 40 / L 8 / D 16

3.9overall
#1351829 rating ±44
MiMo-V2.6-Flash output

MiMo-V2.6-Flash

Xiaomi / Sep 21, 2026 / openrouter

Busey likeness1.8
Face coherence6.0
Aesthetics5.4
Prompt adherence6.5

1 judged output · judge spread σ 0.73 · W 35 / L 12 / D 17

3.9overall
#1361778 rating ±43
GLM 5.1 output

GLM 5.1

Z.ai / Apr 7, 2026 / openrouter

Busey likeness2.3
Face coherence5.6
Aesthetics4.9
Prompt adherence5.8

1 judged output · judge spread σ 0.84 · W 29 / L 11 / D 26

3.9overall
#1371760 rating ±44
Muse Spark Open 816B A42B output

Muse Spark Open 816B A42B

Meta Models / Oct 15, 2026 / direct api

Busey likeness2.3
Face coherence5.0
Aesthetics5.4
Prompt adherence6.0

1 judged output · judge spread σ 1.03 · W 26 / L 13 / D 25

3.9overall
#1381647 rating ±42
Qwen3.7 Flash output

Qwen3.7 Flash

Qwen / Jul 27, 2026 / openrouter

Busey likeness1.7
Face coherence6.0
Aesthetics5.7
Prompt adherence6.7

1 judged output · judge spread σ 0.48 · W 19 / L 21 / D 28

3.9overall
#1391564 rating ±43
DeepSeek V4 Flash output

DeepSeek V4 Flash

DeepSeek / Apr 24, 2026 / openrouter

Busey likeness1.9
Face coherence6.0
Aesthetics5.4
Prompt adherence6.1

1 judged output · judge spread σ 0.73 · W 16 / L 33 / D 17

3.9overall
#1401975 rating ±44
KAT-Coder-Pro V2.5 output

KAT-Coder-Pro V2.5

Kwaipilot / Jul 10, 2026 / openrouter

Busey likeness2.4
Face coherence4.9
Aesthetics4.4
Prompt adherence6.4

1 judged output · judge spread σ 0.86 · W 46 / L 3 / D 15

3.8overall
#1411681 rating ±44
Grok 4.20 output

Grok 4.20

xAI / Feb 17, 2026 / openrouter

Busey likeness1.6
Face coherence6.2
Aesthetics5.4
Prompt adherence6.4

1 judged output · judge spread σ 0.68 · W 23 / L 19 / D 22

3.8overall
#1421680 rating ±44
GPT-5.1-Codex output

GPT-5.1-Codex

OpenAI / Nov 13, 2025 / openrouter

Busey likeness3.2
Face coherence3.9
Aesthetics3.5
Prompt adherence5.8

1 judged output · judge spread σ 0.28 · W 23 / L 18 / D 23

3.8overall
#1431624 rating ±44
Gemma 4 31B output

Gemma 4 31B

Google / Apr 2, 2026 / openrouter

Busey likeness2.1
Face coherence5.7
Aesthetics4.5
Prompt adherence6.2

1 judged output · judge spread σ 0.90 · W 13 / L 18 / D 33

3.8overall
#1441522 rating ±44
Grok 4.3 output

Grok 4.3

xAI / Apr 17, 2026 / openrouter

Busey likeness1.8
Face coherence6.5
Aesthetics5.0
Prompt adherence5.6

1 judged output · judge spread σ 0.56 · W 15 / L 34 / D 15

3.8overall
#1451502 rating ±44
Claude Haiku 4.5 output

Claude Haiku 4.5

Anthropic / Oct 15, 2025 / openrouter

Busey likeness2.1
Face coherence5.3
Aesthetics4.8
Prompt adherence6.2

1 judged output · judge spread σ 0.86 · W 9 / L 29 / D 24

3.8overall
#1461939 rating ±44
MiniMax M3 output

MiniMax M3

MiniMax / May 31, 2026 / openrouter

Busey likeness1.7
Face coherence5.2
Aesthetics5.4
Prompt adherence6.6

1 judged output · judge spread σ 0.75 · W 46 / L 3 / D 15

3.7overall
#1471623 rating ±44
Ling 3.0 Flash VL output

Ling 3.0 Flash VL

inclusionAI / Sep 4, 2026 / openrouter

Busey likeness1.6
Face coherence5.3
Aesthetics5.6
Prompt adherence6.5

1 judged output · judge spread σ 0.63 · W 15 / L 15 / D 34

3.7overall
#1481528 rating ±44
Claude Sonnet 4 output

Claude Sonnet 4

Anthropic / May 22, 2025 / openrouter

Busey likeness2.1
Face coherence5.1
Aesthetics4.5
Prompt adherence6.3

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

3.7overall
#1491464 rating ±41
DeepSeek V3.2 Exp output

DeepSeek V3.2 Exp

DeepSeek / Sep 29, 2025 / openrouter

Busey likeness1.9
Face coherence5.6
Aesthetics5.0
Prompt adherence5.7

1 judged output · judge spread σ 0.70 · W 12 / L 38 / D 22

3.7overall
#1501447 rating ±44
Qwen3.5-122B-A10B output

Qwen3.5-122B-A10B

Qwen / Feb 25, 2026 / openrouter

Busey likeness2.5
Face coherence5.0
Aesthetics4.2
Prompt adherence5.6

1 judged output · judge spread σ 0.58 · W 6 / L 33 / D 23

3.7overall
← PreviousPage 6 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