ArtifactsBench leaderboard
As of November 6, 2026, among the results listed here, inclusionAI Ling 3.0 Flash has the highest reported ArtifactsBench score, 77, published by inclusionAI, ahead of MiniMax M2 at 66.8. 3 models have a ArtifactsBench result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
3 models ranked · 2 makers
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Ling 3.0 Flash | 77 | Not published | inclusionAI | July 23, 2026 (model release) · read from the maker's chart |
| 2 | MiniMax M2Retired | 66.8 | Not published | MiniMax | October 23, 2025 (model release) |
| 3 | Ling 3.0 Tiny | 47.9 | Thinking | inclusionAI | August 6, 2026 (model release) · read from the maker's chart |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- Settings differ between makers. Check the Setting column before comparing two scores.
- Spread
- 77 to 47.9 across 3 models.
- Freshness
- Newest result published August 6, 2026; oldest October 23, 2025.
- Charts
- Some values were read from charts in the announcements. Two independent readings had to match exactly.
What ArtifactsBench measures
ArtifactsBench asks models to generate code for visual artifacts, and its score reflects the visual and interactive quality of the resulting outputs. Source: ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation