VisualArtifactSpec - Total Score: leaderboard

Metric: Total score S = B + adjustment (-50 to 100). Source: accio-lab.github.io. Saturation forecast: Around March 2027. 9 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraMax70.52#7
2GPT-6.1 SolMax69.37#12
3Claude Opus 5.5Max65.03#6
4Kimi K3.1 ProMax62.38#32
5DeepSeek V4.1 FlashMax60.03#67
6Qwen 3.8 MaxxHigh51.95#63
7Kimi K3Max50.7#60
8Gemini 4 ArgonHigh47.28#14
9Claude Sonnet 5Max42.12#116

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=visualartifactspec-total-score · How It Works · Data refreshed daily, snapshot 2026-11-18.