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

276–300 of 306 results
#2761307 rating ±52
Granite 4.1 8B output

Granite 4.1 8B

IBM / Apr 30, 2026 / openrouter

Busey likeness0.6
Face coherence2.1
Aesthetics2.1
Prompt adherence2.2

1 judged output · judge spread σ 0.56 · W 16 / L 9 / D 21

1.4overall
#2771215 rating ±51
Gemini 3.5 Flash-Lite output

Gemini 3.5 Flash-Lite

Google / Jul 21, 2026 / openrouter

Busey likeness0.5
Face coherence1.6
Aesthetics3.8
Prompt adherence1.8

1 judged output · judge spread σ 0.48 · W 3 / L 10 / D 35

1.4overall
#2781168 rating ±52
Llama 3.3 Nemotron Super 49B V1.5 output

Llama 3.3 Nemotron Super 49B V1.5

NVIDIA / Jul 25, 2025 / openrouter

Busey likeness0.7
Face coherence2.1
Aesthetics1.7
Prompt adherence2.2

1 judged output · judge spread σ 0.57 · W 3 / L 14 / D 29

1.4overall
#2791367 rating ±52
Nova Pro 1.0 output

Nova Pro 1.0

Amazon / Dec 5, 2024 / openrouter

Busey likeness0.6
Face coherence2.3
Aesthetics1.8
Prompt adherence2.2

1 judged output · judge spread σ 0.54 · W 17 / L 2 / D 27

1.3overall
#2801237 rating ±52
Qwen3 30B A3B output

Qwen3 30B A3B

Qwen / Apr 28, 2025 / openrouter

Busey likeness0.5
Face coherence1.7
Aesthetics2.9
Prompt adherence1.8

1 judged output · judge spread σ 0.36 · W 8 / L 8 / D 30

1.3overall
#2811221 rating ±52
Trinity Large Thinking output

Trinity Large Thinking

Arcee AI / Apr 1, 2026 / openrouter

Busey likeness0.4
Face coherence2.1
Aesthetics2.7
Prompt adherence1.6

1 judged output · judge spread σ 0.68 · W 4 / L 6 / D 36

1.3overall
#2821193 rating ±51
Nemotron Nano 12B 2 VL (free) output

Nemotron Nano 12B 2 VL (free)

NVIDIA / Oct 28, 2025 / openrouter

Busey likeness0.5
Face coherence2.2
Aesthetics1.9
Prompt adherence2.0

1 judged output · judge spread σ 0.52 · W 5 / L 11 / D 32

1.3overall
#2831150 rating ±52
Ministral 3 3B 2512 output

Ministral 3 3B 2512

Mistral / Dec 2, 2025 / openrouter

Busey likeness0.5
Face coherence1.8
Aesthetics2.7
Prompt adherence1.6

1 judged output · judge spread σ 0.48 · W 4 / L 15 / D 27

1.3overall
#2841064 rating ±51
Command R (08-2024) output

Command R (08-2024)

Cohere / Aug 30, 2024 / openrouter

Busey likeness0.5
Face coherence2.0
Aesthetics2.5
Prompt adherence1.9

1 judged output · judge spread σ 0.50 · W 2 / L 24 / D 22

1.3overall
#2851305 rating ±54
Mistral Small 3 output

Mistral Small 3

Mistral / Jan 30, 2025 / openrouter

Busey likeness0.4
Face coherence1.8
Aesthetics3.0
Prompt adherence1.2

1 judged output · judge spread σ 0.34 · W 10 / L 1 / D 31

1.2overall
#2861259 rating ±51
Qwen3 VL 30B A3B Thinking output

Qwen3 VL 30B A3B Thinking

Qwen / Oct 6, 2025 / openrouter

Busey likeness0.5
Face coherence2.2
Aesthetics1.6
Prompt adherence2.0

1 judged output · judge spread σ 0.52 · W 11 / L 8 / D 29

1.2overall
#2871184 rating ±51
Nemotron Nano 9B V2 (free) output

Nemotron Nano 9B V2 (free)

NVIDIA / Aug 18, 2025 / openrouter

Busey likeness0.5
Face coherence2.2
Aesthetics1.6
Prompt adherence2.0

1 judged output · judge spread σ 0.44 · W 5 / L 12 / D 31

1.2overall
#2881106 rating ±51
Solar Pro 3 output

Solar Pro 3

Upstage / Jan 27, 2026 / openrouter

Busey likeness0.7
Face coherence1.8
Aesthetics1.7
Prompt adherence1.8

1 judged output · judge spread σ 0.24 · W 0 / L 17 / D 31

1.2overall
#2891093 rating ±54
Command R7B (12-2024) output

Command R7B (12-2024)

Cohere / Dec 14, 2024 / openrouter

Busey likeness0.4
Face coherence1.9
Aesthetics1.9
Prompt adherence2.0

1 judged output · judge spread σ 0.41 · W 1 / L 14 / D 27

1.2overall
#2901278 rating ±54
GPT-4 Turbo output

GPT-4 Turbo

OpenAI / Apr 9, 2024 / openrouter

Busey likeness0.4
Face coherence2.0
Aesthetics2.2
Prompt adherence1.2

1 judged output · judge spread σ 0.42 · W 11 / L 3 / D 28

1.1overall
#2911122 rating ±60
Gemma 3 4B output

Gemma 3 4B

Google / Mar 13, 2025 / openrouter

Busey likeness0.4
Face coherence1.5
Aesthetics2.5
Prompt adherence1.4

1 judged output · judge spread σ 0.34 · W 5 / L 10 / D 19

1.1overall
#2921071 rating ±57
GPT-3.5 Turbo Instruct output

GPT-3.5 Turbo Instruct

OpenAI / Sep 18, 2023 / openrouter

Busey likeness0.5
Face coherence1.8
Aesthetics2.0
Prompt adherence1.5

1 judged output · judge spread σ 0.44 · W 2 / L 15 / D 21

1.1overall
#293979 rating ±62
Claude 3 Haiku output

Claude 3 Haiku

Anthropic / Mar 13, 2024 / openrouter

Busey likeness0.3
Face coherence1.1
Aesthetics3.4
Prompt adherence1.1

1 judged output · judge spread σ 0.24 · W 2 / L 18 / D 12

1.1overall
#2941238 rating ±75
Hermes 4 70B output

Hermes 4 70B

Nous / Aug 26, 2025 / openrouter

Busey likeness0.5
Face coherence1.7
Aesthetics1.6
Prompt adherence1.4

1 judged output · judge spread σ 0.36 · W 5 / L 0 / D 17

1.0overall
#2951063 rating ±101
Phi 4 output

Phi 4

Microsoft / Dec 12, 2024 / openrouter

Busey likeness0.3
Face coherence1.0
Aesthetics2.4
Prompt adherence1.1

1 judged output · judge spread σ 0.18 · W 4 / L 6 / D 2

0.9overall
#296906 rating ±82
LFM2.5 8B A1B output

LFM2.5 8B A1B

LiquidAI / May 28, 2026 / direct api

Busey likeness0.5
Face coherence1.2
Aesthetics1.6
Prompt adherence1.3

1 judged output · judge spread σ 0.73 · W 0 / L 11 / D 7

0.9overall
#2971211 rating ±143
Mistral Nemo output

Mistral Nemo

Mistral / Jul 19, 2024 / openrouter

Busey likeness0.3
Face coherence0.8
Aesthetics2.0
Prompt adherence0.9

1 judged output · judge spread σ 0.24 · W 2 / L 0 / D 4

0.8overall
#298982 rating ±143
Qwen3 VL 32B Instruct output

Qwen3 VL 32B Instruct

Qwen / Oct 23, 2025 / openrouter

Busey likeness0.2
Face coherence1.2
Aesthetics1.3
Prompt adherence1.0

1 judged output · judge spread σ 0.24 · W 0 / L 3 / D 3

0.7overall
#2991539 rating ±94
LFM2.5-1.2B-Instruct (free) output

LFM2.5-1.2B-Instruct (free)

LiquidAI / Jan 20, 2026 / openrouter

Busey likeness0.2
Face coherence0.6
Aesthetics0.6
Prompt adherence0.5

1 judged output · judge spread σ 0.18 · W 2 / L 0 / D 12

0.4overall
#3001513 rating ±111
Nova Micro 1.0 output

Nova Micro 1.0

Amazon / Dec 5, 2024 / openrouter

Busey likeness0.2
Face coherence0.4
Aesthetics1.0
Prompt adherence0.7

1 judged output · judge spread σ 0.16 · W 0 / L 0 / D 10

0.4overall
← PreviousPage 12 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