#511738 rating ±71
Claude Sonnet 5
Anthropic / Jun 30, 2026 / openrouter
1 judged output · judge spread σ 0.61 · W 16 / L 6 / D 2
4.5overall
BuseyBenchcreative model benchmarkSVG models testedBuseyBenchcreative model benchmarkSVG models testedLeaderboard
One output per model, independent judge scores, and close-score pairwise tie-breaks. The best Gary Busey portraits rise to the top.
Official standings
Anthropic / Jun 30, 2026 / openrouter
1 judged output · judge spread σ 0.61 · W 16 / L 6 / D 2
MiniMax / Dec 23, 2025 / openrouter
1 judged output · judge spread σ 0.72 · W 10 / L 10 / D 4
OpenAI / Jul 9, 2026 / openrouter
1 judged output · judge spread σ 0.47 · W 0 / L 14 / D 10
ByteDance Seed / Jun 23, 2026 / openrouter
1 judged output · judge spread σ 0.73 · W 0 / L 14 / D 10
MoonshotAI / Jun 12, 2026 / openrouter
1 judged output · judge spread σ 0.35 · W 12 / L 3 / D 9
Google / Jun 17, 2025 / openrouter
1 judged output · judge spread σ 0.57 · W 2 / L 17 / D 7
OpenAI / Dec 10, 2025 / openrouter
1 judged output · judge spread σ 0.43 · W 16 / L 4 / D 4
Google / Dec 17, 2025 / openrouter
1 judged output · judge spread σ 0.58 · W 13 / L 1 / D 10
Qwen / Feb 16, 2026 / openrouter
1 judged output · judge spread σ 0.73 · W 12 / L 1 / D 11
Anthropic / Aug 5, 2025 / openrouter
1 judged output · judge spread σ 0.79 · W 8 / L 3 / D 13
Meta / Apr 8, 2026 / direct api
1 judged output · judge spread σ 1.01 · W 23 / L 0 / D 1
Google / May 7, 2025 / openrouter
1 judged output · judge spread σ 0.70 · W 8 / L 7 / D 9
Anthropic / May 22, 2025 / openrouter
1 judged output · judge spread σ 0.61 · W 5 / L 7 / D 12
DeepSeek / Apr 24, 2026 / openrouter
1 judged output · judge spread σ 0.85 · W 5 / L 7 / D 12
MoonshotAI / Sep 4, 2025 / openrouter
1 judged output · judge spread σ 0.49 · W 1 / L 12 / D 11
ByteDance Seed / Mar 10, 2026 / openrouter
1 judged output · judge spread σ 0.29 · W 0 / L 22 / D 2
Switchpoint / Jul 11, 2025 / openrouter
1 judged output · judge spread σ 0.80 · W 24 / L 0 / D 3
Qwen / Apr 27, 2026 / openrouter
1 judged output · judge spread σ 0.69 · W 6 / L 8 / D 11