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

251–268 of 268 results
#2511215 rating ±70
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 10 / D 15

1.2overall
#2521401 rating ±70
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 7 / L 1 / D 17

1.1overall
#2531272 rating ±71
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 4 / L 5 / D 15

1.1overall
#2541208 rating ±71
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 9 / D 13

1.1overall
#2551129 rating ±73
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 12 / D 9

1.1overall
#2561357 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
#2571177 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
#2581031 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
#2591297 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
#2601083 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
#2611539 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
#2621513 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
#2631500 rating ±94
Qwen3 VL 30B A3B Instruct output

Qwen3 VL 30B A3B Instruct

Qwen / Oct 6, 2025 / openrouter

Busey likeness0.0
Face coherence0.4
Aesthetics1.4
Prompt adherence0.5

1 judged output · judge spread σ 0.04 · W 0 / L 0 / D 14

0.4overall
#2641539 rating ±94
GPT-4o output

GPT-4o

OpenAI / May 13, 2024 / openrouter

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

1 judged output · judge spread σ 0.14 · W 2 / L 0 / D 12

0.3overall
#2651500 rating ±94
Granite 4.0 Micro output

Granite 4.0 Micro

IBM / Oct 2, 2025 / openrouter

Busey likeness0.0
Face coherence0.4
Aesthetics1.3
Prompt adherence0.5

1 judged output · judge spread σ 0.05 · W 0 / L 0 / D 14

0.3overall
#2661500 rating ±94
MythoMax 13B output

MythoMax 13B

Gryphe / Jul 2, 2023 / openrouter

Busey likeness0.0
Face coherence0.3
Aesthetics0.9
Prompt adherence0.4

1 judged output · judge spread σ 0.07 · W 0 / L 0 / D 14

0.2overall
#2671409 rating ±101
Llama 3.1 8B Instruct output

Llama 3.1 8B Instruct

Meta / Jul 23, 2024 / openrouter

Busey likeness0.0
Face coherence0.0
Aesthetics0.6
Prompt adherence0.5

1 judged output · judge spread σ 0.05 · W 0 / L 4 / D 8

0.2overall
#2681498 rating ±101
Aion-RP 1.0 (8B) output

Aion-RP 1.0 (8B)

AionLabs / Feb 4, 2025 / openrouter

Busey likeness0.0
Face coherence0.0
Aesthetics0.9
Prompt adherence0.1

1 judged output · judge spread σ 0.06 · W 0 / L 0 / D 12

0.1overall
← PreviousPage 11 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