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
269 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→
268 models ranked3905 official head-to-head verdictsPairwise tie-break active

Official standings

The rankings

26–50 of 268 results
#261708 rating ±71
Qwen3.8 2.4T A95B output

Qwen3.8 2.4T A95B

Qwen / Aug 12, 2026 / openrouter

Busey likeness4.0
Face coherence5.7
Aesthetics6.5
Prompt adherence7.9

1 judged output · judge spread σ 1.35 · W 14 / L 1 / D 9

5.3overall
#271701 rating ±73
Kimi K2.6 output

Kimi K2.6

MoonshotAI / Apr 20, 2026 / openrouter

Busey likeness4.1
Face coherence5.8
Aesthetics5.9
Prompt adherence7.5

1 judged output · judge spread σ 0.73 · W 16 / L 3 / D 4

5.2overall
#281663 rating ±71
Claude Opus 4.5 output

Claude Opus 4.5

Anthropic / Nov 24, 2025 / openrouter

Busey likeness4.3
Face coherence5.5
Aesthetics5.6
Prompt adherence7.4

1 judged output · judge spread σ 0.80 · W 14 / L 3 / D 7

5.2overall
#291436 rating ±73
Claude Opus 4.8 output

Claude Opus 4.8

Anthropic / May 27, 2026 / openrouter

Busey likeness4.0
Face coherence6.3
Aesthetics5.8
Prompt adherence7.4

1 judged output · judge spread σ 0.73 · W 5 / L 9 / D 9

5.2overall
#301294 rating ±71
GPT-5.2-Codex output

GPT-5.2-Codex

OpenAI / Jan 14, 2026 / openrouter

Busey likeness4.1
Face coherence5.9
Aesthetics5.8
Prompt adherence7.1

1 judged output · judge spread σ 0.76 · W 2 / L 15 / D 7

5.2overall
#311696 rating ±71
GPT-5.2 output

GPT-5.2

OpenAI / Dec 10, 2025 / openrouter

Busey likeness4.0
Face coherence5.7
Aesthetics5.7
Prompt adherence7.1

1 judged output · judge spread σ 0.75 · W 15 / L 2 / D 7

5.1overall
#321539 rating ±70
GLM 5V Turbo output

GLM 5V Turbo

Z.ai / Apr 1, 2026 / openrouter

Busey likeness4.0
Face coherence5.8
Aesthetics5.7
Prompt adherence7.2

1 judged output · judge spread σ 0.62 · W 9 / L 6 / D 10

5.1overall
#331327 rating ±71
Claude Opus 4.7 (Fast) output

Claude Opus 4.7 (Fast)

Anthropic / May 12, 2026 / openrouter

Busey likeness4.0
Face coherence5.6
Aesthetics5.9
Prompt adherence7.1

1 judged output · judge spread σ 0.79 · W 3 / L 14 / D 7

5.1overall
#341321 rating ±71
Qwen3.7 Plus output

Qwen3.7 Plus

Qwen / Jun 2, 2026 / openrouter

Busey likeness3.5
Face coherence7.1
Aesthetics6.2
Prompt adherence6.5

1 judged output · judge spread σ 0.51 · W 2 / L 14 / D 8

5.1overall
#351588 rating ±71
GLM 5.2 output

GLM 5.2

Z.ai / Jun 16, 2026 / openrouter

Busey likeness3.5
Face coherence6.0
Aesthetics6.1
Prompt adherence7.4

1 judged output · judge spread σ 0.57 · W 12 / L 4 / D 8

5.0overall
#361583 rating ±71
Claude Opus 4.7 output

Claude Opus 4.7

Anthropic / Apr 16, 2026 / openrouter

Busey likeness3.8
Face coherence5.8
Aesthetics5.6
Prompt adherence7.1

1 judged output · judge spread σ 0.64 · W 13 / L 5 / D 6

5.0overall
#371437 rating ±71
Gemini 3.6 Flash output

Gemini 3.6 Flash

Google / Jul 21, 2026 / openrouter

Busey likeness4.2
Face coherence4.5
Aesthetics5.8
Prompt adherence7.2

1 judged output · judge spread σ 0.40 · W 5 / L 7 / D 12

5.0overall
#381718 rating ±73
Grok 4.5 output

Grok 4.5

xAI / Jul 8, 2026 / openrouter

Busey likeness3.4
Face coherence5.9
Aesthetics6.0
Prompt adherence7.6

1 judged output · judge spread σ 0.75 · W 16 / L 1 / D 6

4.9overall
#391477 rating ±71
GPT-5.3-Codex output

GPT-5.3-Codex

OpenAI / Feb 5, 2026 / openrouter

Busey likeness3.7
Face coherence5.3
Aesthetics5.6
Prompt adherence7.4

1 judged output · judge spread σ 0.63 · W 8 / L 8 / D 8

4.9overall
#401368 rating ±73
GPT-5.1-Codex-Max output

GPT-5.1-Codex-Max

OpenAI / Nov 19, 2025 / openrouter

Busey likeness4.0
Face coherence5.4
Aesthetics5.4
Prompt adherence6.7

1 judged output · judge spread σ 0.98 · W 3 / L 9 / D 11

4.9overall
#411142 rating ±71
Qwen3.5 Plus 2026-02-15 output

Qwen3.5 Plus 2026-02-15

Qwen / Feb 16, 2026 / openrouter

Busey likeness4.0
Face coherence5.5
Aesthetics5.4
Prompt adherence6.8

1 judged output · judge spread σ 0.84 · W 0 / L 19 / D 5

4.9overall
#421472 rating ±71
Claude Sonnet 4.6 output

Claude Sonnet 4.6

Anthropic / Feb 17, 2026 / openrouter

Busey likeness3.7
Face coherence5.3
Aesthetics5.7
Prompt adherence6.7

1 judged output · judge spread σ 0.77 · W 7 / L 11 / D 6

4.8overall
#431243 rating ±71
GPT-5.3 Chat output

GPT-5.3 Chat

OpenAI / Mar 3, 2026 / openrouter

Busey likeness3.4
Face coherence6.0
Aesthetics5.2
Prompt adherence7.3

1 judged output · judge spread σ 0.68 · W 0 / L 17 / D 7

4.8overall
#441793 rating ±71
Muse Spark 1.1 output

Muse Spark 1.1

Meta / Jul 9, 2026 / direct api

Busey likeness3.0
Face coherence6.4
Aesthetics6.0
Prompt adherence6.8

1 judged output · judge spread σ 0.67 · W 15 / L 2 / D 7

4.7overall
#451401 rating ±70
Sonar Pro output

Sonar Pro

Perplexity / Jan 21, 2025 / openrouter

Busey likeness3.6
Face coherence4.9
Aesthetics6.5
Prompt adherence6.4

1 judged output · judge spread σ 0.44 · W 4 / L 13 / D 8

4.7overall
#461988 rating ±71
Grok 4.6 output

Grok 4.6

SpaceXAI / Aug 12, 2026 / openrouter

Busey likeness3.2
Face coherence5.2
Aesthetics6.0
Prompt adherence7.0

1 judged output · judge spread σ 0.25 · W 21 / L 1 / D 2

4.6overall
#471837 rating ±71
Qwen3.7 Max output

Qwen3.7 Max

Qwen / May 19, 2026 / openrouter

Busey likeness3.2
Face coherence5.7
Aesthetics5.7
Prompt adherence7.0

1 judged output · judge spread σ 1.02 · W 17 / L 2 / D 5

4.6overall
#481534 rating ±71
GPT-5.4 output

GPT-5.4

OpenAI / Mar 5, 2026 / openrouter

Busey likeness3.1
Face coherence5.8
Aesthetics5.8
Prompt adherence6.7

1 judged output · judge spread σ 0.50 · W 8 / L 11 / D 5

4.6overall
#491493 rating ±71
o3 output

o3

OpenAI / Apr 16, 2025 / openrouter

Busey likeness3.1
Face coherence5.9
Aesthetics5.6
Prompt adherence6.9

1 judged output · judge spread σ 0.43 · W 6 / L 11 / D 7

4.6overall
#501818 rating ±71
Hy3 (free) output

Hy3 (free)

Tencent / Apr 22, 2026 / openrouter

Busey likeness2.7
Face coherence5.8
Aesthetics6.2
Prompt adherence7.1

1 judged output · judge spread σ 0.56 · W 15 / L 1 / D 8

4.5overall
← PreviousPage 2 of 11Next →
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