A task with its own rules.
A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.
- Organisation
- Design Arena
- Version
- 2026
Loading benchmark header
Loading benchmark registry
Multimodal / Benchmark profile
A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.
Observed results
20 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Kimi K3 | #1 | kimi-k3 | Moonshot AI | 1386 | elo |
| Claude Opus 5 | #2 | claude-opus-5 | Anthropic | 1341 | elo |
| GLM-5.2 | #3 | glm-5-2 | Z.AI | 1341 | elo |
| Claude Fable 5 | #4 | claude-fable-5 | Anthropic | 1332 | elo |
| Claude Opus 4.6 | #5 | claude-opus-4-6 | Anthropic | 1325 | elo |
| Claude Opus 4.7 | #6 | claude-opus-4-7 | Anthropic | 1325 | elo |
| Grok 4.5 | #7 | grok-4-5 | xAI | 1325 | elo |
| Gemini 3.6 Flash | #8 | gemini-3-6-flash | 1319 | elo | |
| Claude Sonnet 4.6 | #9 | claude-sonnet-4-6 | Anthropic | 1314 | elo |
| Claude Sonnet 5 | #10 | claude-sonnet-5 | Anthropic | 1314 | elo |
| MiMo-V2.5-Pro | #11 | mimo-v2-5-pro | Xiaomi | 1309 | elo |
| Kimi K2.6 | #12 | kimi-k2-6 | Moonshot AI | 1306 | elo |
| GLM-5.1 | #13 | glm-5-1 | Z.AI | 1305 | elo |
| Qwen3.7-Max | #14 | qwen-3-7-max | Alibaba Cloud | 1303 | elo |
| Kimi K2.7 Code | #15 | kimi-k2-7-code | Moonshot AI | 1302 | elo |
| GLM-5-Turbo | #16 | glm-5-turbo | Z.AI | 1301 | elo |
| Muse Spark 1.1 | #17 | muse-spark-1-1 | Meta | 1299 | elo |
| Qwen3.7-Plus | #18 | qwen-3-7-plus | Alibaba Cloud | 1297 | elo |
| MiMo-V2.5 | #19 | mimo-v2-5 | Xiaomi | 1295 | elo |
| MiniMax M3 | #20 | minimax-m3 | MiniMax | 1289 | elo |
| Gemini 3.5 Flash | #21 | gemini-3-5-flash | 1285 | elo | |
| GPT-5.5 | #22 | gpt-5-5 | OpenAI | 1282 | elo |
| Kimi K2.5 | #23 | kimi-k2-5 | Moonshot AI | 1279 | elo |
| GLM-5 | #24 | glm-5 | Z.AI | 1278 | elo |
| GLM-5 (Reasoning) | #25 | glm-5-reasoning | Z.AI | 1278 | elo |
| Claude Opus 4.5 | #26 | claude-opus-4-5 | Anthropic | 1277 | elo |
| Claude Opus 4.5 Thinking | #27 | claude-opus-4-5-thinking | Anthropic | 1277 | elo |
| MiniMax M2.7 | #28 | minimax-m2-7 | MiniMax | 1275 | elo |
| Claude Opus 4.8 | #29 | claude-opus-4-8 | Anthropic | 1270 | elo |
| Qwen3.6 Plus | #30 | qwen3-6-plus | Alibaba Cloud | 1265 | elo |
| DeepSeek V4 Pro | #31 | deepseek-v4-pro | DeepSeek | 1264 | elo |
| GLM-5V-Turbo | #32 | glm-5v-turbo | Z.AI | 1258 | elo |
| Grok 4.20 | #33 | grok-4-20 | xAI | 1257 | elo |
| GLM-4.7 | #34 | glm-4-7 | Z.AI | 1255 | elo |
| GPT-5.4 | #35 | gpt-5-4 | OpenAI | 1250 | elo |
| DeepSeek V4 Flash | #36 | deepseek-v4-flash | DeepSeek | 1238 | elo |
| Hy3 | #37 | hy3 | Tencent | 1229 | elo |
| Gemini 3 Flash | #38 | gemini-3-flash | 1226 | elo | |
| Grok 4.3 | #39 | grok-4-3 | xAI | 1225 | elo |
| GPT-5.2 | #40 | gpt-5-2 | OpenAI | 1224 | elo |
| Claude Sonnet 4.5 | #41 | claude-sonnet-4-5 | Anthropic | 1219 | elo |
| Claude Sonnet 4.5 Thinking | #42 | claude-sonnet-4-5-thinking | Anthropic | 1219 | elo |
| GPT-5.1 | #43 | gpt-5-1 | OpenAI | 1217 | elo |
| GPT-5 | #44 | gpt-5 | OpenAI | 1214 | elo |
| Step 3.7 Flash | #45 | step-3-7-flash | StepFun | 1212 | elo |
| Claude 4.1 Opus | #46 | claude-4-1-opus | Anthropic | 1207 | elo |
| DeepSeek V3.2 | #47 | deepseek-v3-2 | DeepSeek | 1204 | elo |
| DeepSeek V3.2 (Thinking) | #48 | deepseek-v3-2-thinking | DeepSeek | 1204 | elo |
| GLM-4.5 | #49 | glm-4-5 | Z.AI | 1200 | elo |
| Gemini 2.5 Pro | #50 | gemini-2-5-pro | 1197 | elo | |
| GPT-5.3-Codex | #51 | gpt-5-3-codex | OpenAI | 1193 | elo |
| GPT-5.1-Codex | #52 | gpt-5-1-codex | OpenAI | 1191 | elo |
| GLM-4.5-Air | #53 | glm-4-5-air | Z.AI | 1176 | elo |
| Claude 4 Sonnet | #54 | claude-4-sonnet | Anthropic | 1175 | elo |
| Trinity-Large-Preview | #55 | trinity-large-preview | Arcee AI | 1165 | elo |
| Trinity-Large-Thinking | #56 | trinity-large-thinking | Arcee AI | 1165 | elo |
| Claude Haiku 4.5 | #57 | claude-haiku-4-5 | Anthropic | 1152 | elo |
| Claude Haiku 4.5 Thinking | #58 | claude-haiku-4-5-thinking | Anthropic | 1152 | elo |
| DeepSeek V3.1 | #59 | deepseek-v3-1 | DeepSeek | 1152 | elo |
| DeepSeek V3 | #60 | deepseek-v3 | DeepSeek | 1150 | elo |
| Qwen3 Max | #61 | qwen3-max | Alibaba Cloud | 1148 | elo |
| Gemini 2.5 Flash | #62 | gemini-2-5-flash | 1145 | elo | |
| Nemotron 3 Ultra | #63 | nemotron-3-ultra | NVIDIA | 1129 | elo |
| Mistral Medium 3 | #64 | mistral-medium-3 | Mistral AI | 1109 | elo |
| Kimi K2 | #65 | kimi-k2 | Moonshot AI | 1080 | elo |
| GPT-4.1 | #66 | gpt-4-1 | OpenAI | 1068 | elo |
| o3 | #67 | o3 | OpenAI | 1067 | elo |
| GPT-4.1 mini | #68 | gpt-4-1-mini | OpenAI | 1027 | elo |
| GPT-4.1 nano | #69 | gpt-4-1-nano | OpenAI | 1003 | elo |
| GPT-OSS 120B | #70 | gpt-oss-120b | OpenAI | 998 | elo |
| Llama 4 Maverick | #71 | llama-4-maverick | Meta | 901 | elo |
| GPT-OSS 20B | #72 | gpt-oss-20b | OpenAI | 882 | elo |
| GPT-4o | #73 | gpt-4o | OpenAI | 861 | elo |
| Llama 4 Scout | #74 | llama-4-scout | Meta | 780 | elo |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Kimi K3Moonshot AI | Open weights | Source carrier | 1386 elo |
| 02 | Claude Opus 5Anthropic | Closed weights | Source carrier | 1341 elo |
| 03 | GLM-5.2Z.AI | Open weights | Source carrier | 1341 elo |
| 04 | Claude Fable 5Anthropic | Closed weights | Source carrier | 1332 elo |
| 05 | Claude Opus 4.6Anthropic | Closed weights | Source carrier | 1325 elo |
| 06 | Claude Opus 4.7Anthropic | Closed weights | Source carrier | 1325 elo |
| 07 | Grok 4.5xAI | Closed weights | Source carrier | 1325 elo |
| 08 | Gemini 3.6 FlashGoogle | Closed weights | Source carrier | 1319 elo |
| 09 | Claude Sonnet 4.6Anthropic | Closed weights | Source carrier | 1314 elo |
| 10 | Claude Sonnet 5Anthropic | Closed weights | Source carrier | 1314 elo |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Exact BenchLM registry variant Kimi K3; bulk export does not retain a complete upstream harness configuration.Kimi K3Exact identitySource label without a registered configuration ID Canonical product: kimi-k3 | 1377 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration.Claude Opus 5Exact identitySource label without a registered configuration ID Canonical product: claude-opus-5 | 1341 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GLM-5.2; bulk export does not retain a complete upstream harness configuration.GLM-5.2Exact identitySource label without a registered configuration ID Canonical product: glm-5-2 | 1341 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Fable 5; bulk export does not retain a complete upstream harness configuration.Claude Fable 5Exact identitySource label without a registered configuration ID Canonical product: claude-fable-5 | 1324 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Grok 4.5; bulk export does not retain a complete upstream harness configuration.Grok 4.5Exact identitySource label without a registered configuration ID Canonical product: grok-4-5 | 1321 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.Claude Opus 4.7Exact identityclaude-opus-4-7-max Canonical product: claude-opus-4-7 | 1320 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.7; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.7Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-7 | 1320 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.6; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.6Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-6 | 1319 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.6 (Adaptive); bulk export does not retain a complete upstream harness configuration.Claude Opus 4.6Exact identityclaude-opus-4-6-max Canonical product: claude-opus-4-6 | 1319 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Gemini 3.6 Flash; bulk export does not retain a complete upstream harness configuration.Gemini 3.6 FlashExact identitySource label without a registered configuration ID Canonical product: gemini-3-6-flash | 1319 elo | Source carriersource-checkedVersion & system2026 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.