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
306 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→
306 models ranked7103 official head-to-head verdictsPairwise tie-break active

Official standings

The rankings

26–50 of 306 results
#261543 rating ±64
GPT-5.6 Terra output

GPT-5.6 Terra

OpenAI / Jul 9, 2026 / openrouter

Busey likeness4.9
Face coherence6.3
Aesthetics7.4
Prompt adherence8.3

1 judged output · judge spread σ 0.87 · W 5 / L 13 / D 12

6.1overall
#271688 rating ±64
GPT-5.5 output

GPT-5.5

OpenAI / Apr 24, 2026 / openrouter

Busey likeness5.1
Face coherence6.0
Aesthetics6.8
Prompt adherence8.2

1 judged output · judge spread σ 0.84 · W 13 / L 5 / D 12

6.0overall
#281246 rating ±64
MiMo-V2.6-Pro output

MiMo-V2.6-Pro

Xiaomi / Sep 21, 2026 / openrouter

Busey likeness5.4
Face coherence5.5
Aesthetics7.3
Prompt adherence7.2

1 judged output · judge spread σ 0.89 · W 0 / L 23 / D 7

6.0overall
#291691 rating ±64
Gemini 3.5 Flash output

Gemini 3.5 Flash

Google / May 19, 2026 / openrouter

Busey likeness5.1
Face coherence5.5
Aesthetics6.6
Prompt adherence8.2

1 judged output · judge spread σ 1.16 · W 12 / L 4 / D 14

5.9overall
#301634 rating ±64
Claude Fable 5 output

Claude Fable 5

Anthropic / Jun 9, 2026 / openrouter

Busey likeness4.9
Face coherence5.9
Aesthetics7.0
Prompt adherence8.1

1 judged output · judge spread σ 0.79 · W 12 / L 9 / D 9

5.9overall
#311767 rating ±64
Fugu Ultra output

Fugu Ultra

Sakana / Jun 22, 2026 / openrouter

Busey likeness4.9
Face coherence6.0
Aesthetics6.6
Prompt adherence8.2

1 judged output · judge spread σ 1.06 · W 16 / L 2 / D 12

5.8overall
#321712 rating ±64
Muse Spark 1.3 Contributor output

Muse Spark 1.3 Contributor

Meta / Sep 2, 2026 / direct api

Busey likeness4.9
Face coherence5.9
Aesthetics6.6
Prompt adherence8.2

1 judged output · judge spread σ 0.88 · W 16 / L 6 / D 8

5.8overall
#331618 rating ±64
Ember-1 output

Ember-1

Fireworks / Sep 23, 2026 / openrouter

Busey likeness5.1
Face coherence5.5
Aesthetics6.5
Prompt adherence7.9

1 judged output · judge spread σ 0.81 · W 11 / L 9 / D 10

5.8overall
#341579 rating ±62
Qwen3.8 Max (0902) output

Qwen3.8 Max (0902)

Qwen / Sep 2, 2026 / openrouter

Busey likeness4.4
Face coherence6.9
Aesthetics7.0
Prompt adherence7.8

1 judged output · judge spread σ 0.88 · W 10 / L 11 / D 11

5.8overall
#351292 rating ±60
Qwen3.8 27B output

Qwen3.8 27B

Qwen / Aug 14, 2026 / openrouter

Busey likeness4.5
Face coherence6.4
Aesthetics7.1
Prompt adherence7.9

1 judged output · judge spread σ 0.85 · W 0 / L 23 / D 11

5.8overall
#361581 rating ±60
Muse Spark 1.3 output

Muse Spark 1.3

Meta / Sep 2, 2026 / openrouter

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

1 judged output · judge spread σ 0.37 · W 11 / L 10 / D 13

5.7overall
#371342 rating ±60
GPT-5.6 Luna Pro output

GPT-5.6 Luna Pro

OpenAI / Jul 9, 2026 / openrouter

Busey likeness4.4
Face coherence6.0
Aesthetics7.3
Prompt adherence8.1

1 judged output · judge spread σ 1.04 · W 4 / L 23 / D 7

5.7overall
#381845 rating ±62
GLM 5.3 Prime output

GLM 5.3 Prime

Z.ai / Aug 14, 2026 / openrouter

Busey likeness4.1
Face coherence6.4
Aesthetics6.9
Prompt adherence7.9

1 judged output · judge spread σ 1.18 · W 24 / L 0 / D 8

5.6overall
#391791 rating ±62
Qwen3.8 Flash output

Qwen3.8 Flash

Qwen / Aug 26, 2026 / openrouter

Busey likeness4.1
Face coherence6.1
Aesthetics7.1
Prompt adherence8.2

1 judged output · judge spread σ 0.58 · W 22 / L 1 / D 9

5.6overall
#401672 rating ±62
Nex-N2.5-Pro output

Nex-N2.5-Pro

Nex AGI / Sep 8, 2026 / openrouter

Busey likeness4.4
Face coherence5.8
Aesthetics6.9
Prompt adherence7.9

1 judged output · judge spread σ 0.97 · W 16 / L 3 / D 13

5.6overall
#411632 rating ±58
Muse Spark 1.2 output

Muse Spark 1.2

Meta / Aug 5, 2026 / openrouter

Busey likeness4.5
Face coherence6.2
Aesthetics6.2
Prompt adherence7.9

1 judged output · judge spread σ 0.74 · W 17 / L 10 / D 9

5.6overall
#421370 rating ±58
Muse Spark 1.2 Contributor output

Muse Spark 1.2 Contributor

Meta / Unknown / direct api

Busey likeness4.4
Face coherence6.4
Aesthetics6.4
Prompt adherence7.8

1 judged output · judge spread σ 0.83 · W 5 / L 20 / D 11

5.6overall
#431557 rating ±64
GLM 5.3 FlashX output

GLM 5.3 FlashX

Z.ai / Aug 26, 2026 / openrouter

Busey likeness4.2
Face coherence5.9
Aesthetics7.3
Prompt adherence7.9

1 judged output · judge spread σ 0.84 · W 11 / L 7 / D 12

5.5overall
#441501 rating ±64
Claude Opus 4.6 output

Claude Opus 4.6

Anthropic / Feb 4, 2026 / openrouter

Busey likeness4.6
Face coherence6.0
Aesthetics6.1
Prompt adherence7.5

1 judged output · judge spread σ 1.37 · W 7 / L 8 / D 15

5.5overall
#451393 rating ±62
Nex-N2-Pro output

Nex-N2-Pro

Nex AGI / Jun 2, 2026 / openrouter

Busey likeness4.6
Face coherence5.5
Aesthetics6.4
Prompt adherence7.4

1 judged output · judge spread σ 0.66 · W 4 / L 17 / D 11

5.5overall
#461306 rating ±62
GPT-5.2 Pro output

GPT-5.2 Pro

OpenAI / Dec 10, 2025 / openrouter

Busey likeness4.0
Face coherence6.6
Aesthetics6.9
Prompt adherence7.5

1 judged output · judge spread σ 0.47 · W 2 / L 21 / D 9

5.5overall
#471651 rating ±60
Ox Alpha output

Ox Alpha

Stealth / Aug 20, 2026 / openrouter

Busey likeness4.1
Face coherence6.0
Aesthetics6.8
Prompt adherence7.5

1 judged output · judge spread σ 0.52 · W 14 / L 6 / D 14

5.4overall
#481408 rating ±62
Qwen3.8 Max output

Qwen3.8 Max

Qwen / Aug 3, 2026 / openrouter

Busey likeness4.1
Face coherence6.1
Aesthetics6.4
Prompt adherence7.9

1 judged output · judge spread σ 1.16 · W 4 / L 17 / D 11

5.4overall
#491227 rating ±62
Claude Opus 4.8 (Fast) output

Claude Opus 4.8 (Fast)

Anthropic / May 27, 2026 / openrouter

Busey likeness3.7
Face coherence7.6
Aesthetics6.2
Prompt adherence7.1

1 judged output · judge spread σ 0.40 · W 3 / L 26 / D 3

5.4overall
#501881 rating ±64
Qwen3.8 Omni Flash output

Qwen3.8 Omni Flash

Qwen / Sep 18, 2026 / openrouter

Busey likeness4.0
Face coherence5.6
Aesthetics6.7
Prompt adherence7.7

1 judged output · judge spread σ 1.02 · W 23 / L 0 / D 7

5.3overall
← PreviousPage 2 of 13Next →
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