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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6 Astra | Max | 70.52 | #7 |
| 2 | GPT-6.1 Sol | Max | 69.37 | #12 |
| 3 | Claude Opus 5.5 | Max | 65.03 | #6 |
| 4 | Kimi K3.1 Pro | Max | 62.38 | #32 |
| 5 | DeepSeek V4.1 Flash | Max | 60.03 | #67 |
| 6 | Qwen 3.8 Max | xHigh | 51.95 | #63 |
| 7 | Kimi K3 | Max | 50.7 | #60 |
| 8 | Gemini 4 Argon | High | 47.28 | #14 |
| 9 | Claude Sonnet 5 | Max | 42.12 | #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.