# Design Bench (Internal, Elo) (Design Bench)

> Moonshot AI's internal graphic-design benchmark using direct and reference-image few-shot prompting, reported as Elo.

Canonical page: https://benchlm.ai/benchmarks/kimidesignbench

- Category: [Agentic](/agentic)
- Last updated: October 29, 2026

## About Design Bench

- Year: 2026
- Tasks: Graphic design requests
- Format: Elo
- Difficulty: Professional graphic design
- Paper: [Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence](https://www.kimi.ai/blog/kimi-k3-1-pro)

Uses the same harness and calibrated automated grader as DECK-Arena. BenchLM stores the provider-published internal benchmark value as display-only launch evidence and does not treat it as an independently reproducible score.

Design Bench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | Moonshot AI | 957 |

## FAQ

### What does Design Bench measure?

Moonshot AI's internal graphic-design benchmark using direct and reference-image few-shot prompting, reported as Elo.

### Which model scores highest on Design Bench?

Kimi K3.1 Pro by Moonshot AI currently leads with a score of 957 on Design Bench.

### How many models are evaluated on Design Bench?

1 AI models have published results on Design Bench in the BenchLM catalog.

### Does Design Bench affect BenchLM's overall score?

Not directly. Design Bench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.