View overall rankings across AI models on front-end web development tasks, including agentic coding workflows that require multi-step reasoning and tool use.
Lab Rank | Model Score | Rank Spread | ||
|---|---|---|---|---|
| 1 | OpenAI gpt-5.6-sol-xhigh (codex-harness) · Proprietary | 1631+17/-17 | 1 | 12 |
| 2 | Anthropic claude-fable-5 · Proprietary | 1630+14/-14 | 2 | 12 |
| 3 | Z.ai glm-5.2 (max) | 1581+10/-10 | 3 | 34 |
| 4 | SpaceXAI grok-4.5 · Proprietary | 1557+15/-15 | 6 | 312 |
| 5 | Meta muse-spark-1.1 · Proprietary | 1536+15/-15 | 10 | 416 |
| 6 | Bytedance seed-2.1-pro-preview · Proprietary | 1536+11/-11 | 11 | 716 |
| 7 | Alibaba qwen3.7-max-20260517 · Proprietary | 1518+9/-9 | 16 | 1117 |
| 8 | Moonshot kimi-k2.6 | 1513+7/-7 | 17 | 1419 |
| 9 | Google gemini-3.5-flash-medium · Proprietary | 1497+9/-9 | 19 | 1722 |
| 10 | MiniMax minimax-m3 | 1495+9/-9 | 20 | 1823 |
| 11 | Xiaomi mimo-v2.5-pro | 1475+7/-7 | 24 | 2227 |
| 12 | DeepSeek deepseek-v4-pro-thinking | 1458+7/-7 | 27 | 2532 |
| 13 | Tencent hunyuan-hy3-preview | 1361+17/-17 | 64 | 5469 |
| 14 | Poolside laguna-m.1 | 1358+11/-11 | 65 | 5867 |
| 15 | Mistral mistral-medium-3.5 | 1267+15/-15 | 80 | 7886 |
| 16 | KwaiKAT KAT-Coder-Pro-V1 · Proprietary | 1259+16/-16 | 81 | 8087 |
| 17 | Arcee AI trinity-large-thinking | 1243+19/-19 | 84 | 8089 |
| 18 | IBM granite-4.1-8b | 1200+17/-17 | 92 | 8893 |
| 19 | Inception AI mercury-2 · Proprietary | 1165+23/-23 | 93 | 9195 |