Skip to content
Bencher

TestsBenchmarks · Human preference

Design Arena (all categories)

Crowd-voted Bradley-Terry Elo for generated websites, UI, games, slides and other design artifacts.

Elo ratingHigher is betterThe test's websiteOfficial page ↗

The best 15 · 21 models tested

Top 15 · best setting per model · 21 models, 24 results (24 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported
Design Arena (all categories) leaderboard
Thinking levelSetting
1Claude Opus 5.5Anthropic1399Defaultclaude-opus-5-5Independent testIndependentDesign Arena ↗—1 Oct 2026
2GPT-6 AstraOpenAI1388Defaultgpt-6-astraIndependent testIndependentDesign Arena ↗—1 Oct 2026
3Kimi K3Moonshot AI (Kimi)1372Defaultkimi-k3Independent testIndependentDesign Arena ↗—1 Oct 2026
4Muse Spark 1.3Meta (Meta Superintelligence Labs, Muse)1359Defaultmuse-spark-1.3Independent testIndependentDesign Arena ↗—1 Oct 2026
5GPT-5.6 SolOpenAI1345Extra highgpt-5.6-sol-xhighIndependent testIndependentDesign Arena ↗—1 Oct 2026
6Claude Fable 5.1Anthropic1342Defaultclaude-fable-5-1Independent testIndependentDesign Arena ↗—1 Oct 2026
7Claude Opus 5Anthropic1329Defaultclaude-opus-5Independent testIndependentDesign Arena ↗—1 Oct 2026
8DeepSeek V4.1 FlashDeepSeek1329Defaultdeepseek-v4-1-flashIndependent testIndependentDesign Arena ↗—1 Oct 2026
9Muse Spark 1.2Meta (Meta Superintelligence Labs, Muse)1318Defaultmuse-spark-1.2Independent testIndependentDesign Arena ↗—1 Oct 2026
10Claude Fable 5Anthropic1317Defaultclaude-fable-5Independent testIndependentDesign Arena ↗—1 Oct 2026
11Gemini 3.7 FlashGoogle (Gemini / DeepMind)1315Defaultgemini-3.7-flashIndependent testIndependentDesign Arena ↗—1 Oct 2026
12Gemini 3.8 FlashGoogle (Gemini / DeepMind)1310Defaultgemini-3.8-flashIndependent testIndependentDesign Arena ↗—1 Oct 2026
13Qwen3.8 Max (0803)Qwen (Alibaba)1300Defaultqwen3.8-max-previewIndependent testIndependentDesign Arena ↗—1 Oct 2026
14GLM-5.2Z.ai (Zhipu)1297Defaultglm-5.2Independent testIndependentDesign Arena ↗—1 Oct 2026
15Claude Opus 4.6Anthropic1295Defaultclaude-opus-4-6Independent testIndependentDesign Arena ↗—1 Oct 2026
16Gemini 3.6 FlashGoogle (Gemini / DeepMind)1295Defaultgemini-3.6-flashIndependent testIndependentDesign Arena ↗—1 Oct 2026
17GPT-6 SolOpenAI1292Defaultgpt-6-solIndependent testIndependentDesign Arena ↗—1 Oct 2026
18Claude Sonnet 5Anthropic1283Defaultclaude-sonnet-5Independent testIndependentDesign Arena ↗—1 Oct 2026
19Claude Sonnet 4.6Anthropic1282Defaultclaude-sonnet-4-6Independent testIndependentDesign Arena ↗—1 Oct 2026
20Claude Opus 4.8Anthropic1259Defaultclaude-opus-4-8Independent testIndependentDesign Arena ↗—1 Oct 2026
21MiniMax M3MiniMax1254Defaultminimax-m3Independent testIndependentDesign Arena ↗—1 Oct 2026