EnterpriseBench: CoreCraft
Professional Work · 2026-02-18
Score on enterprise agent tasks in a simulated startup world.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 77.4 |
| Claude Opus 5.5 | 74.4 |
| Claude Fable 5 | 70.3 |
| Claude Opus 5 | 68.7 |
| Grok 4.7 | 68.2 |
| Grok 4.6 | 65.6 |
| Muse Spark 1.3 | 61.9 |
| Gemini 3.8 Flash | 58.5 |
| Gemini 3.7 Flash | 55.9 |
| Opus 4.8 | 52.3 |
| GLM-5.3 | 51.8 |
| Muse Glimmer 30B | 51.8 |
| Sonnet 5 | 51.3 |
| GPT-5.5 | 51.3 |
| Gemini 3.5 Flash | 50.8 |
| GLM-5.3 Flash | 46.7 |
| GPT-5.6 Sol | 46.2 |
| DeepSeek V4 Flash Vision Exp | 45.6 |
| GPT-6 Luna | 43.1 |
| GPT-6 Sol | 43.1 |
| Kimi K3 | 43.1 |
| GPT-5.2 | 42.6 |
| GPT-6 Astra | 42.6 |
| GLM-5.2 | 42.1 |
| DeepSeek V4.1 Flash | 41.5 |
| Hy3 | 41.0 |
| Gemini 3.6 Flash | 39.5 |
| GPT-5.4 | 36.4 |
| Opus 4.7 | 35.9 |
| Gemini 3.1 Pro Preview | 27.2 |
| Qwen3.7-Max (source unspecified) | 26.2 |
| Kimi K2.6 | 24.6 |
| DeepSeek-V3.2 | 24.1 |
| Grok 4.1 Fast | 20.5 |
| GPT-5.2-Codex | 20.1 |
| Gemini 3 Flash Preview | 20.0 |
| GLM-5 | 17.4 |
| Sonnet 4.6 | 16.4 |
| Gemini 3 Pro Preview | 14.4 |
| Qwen3.5 Plus (2026-02-15) | 11.3 |