# EnterpriseBench: CoreCraft (Surge) (EnterpriseBench-CoreCraft)

> An enterprise-operations agent benchmark from Surge AI set in a simulated company (CoreCraft), where agents complete multi-step business tasks across internal tools and records.

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

- Category: [Agentic](/agentic)
- Last updated: November 7, 2026

## About EnterpriseBench-CoreCraft

- Year: 2026
- Tasks: Enterprise operations tasks in a simulated company
- Format: Task success (%)
- Difficulty: Multi-step enterprise tool use
- Paper: [Introducing Inkling 2 Small](https://thinkingmachines.ai/news/inkling-2-small/)

Thinking Machines attributes EnterpriseBench to Surge and reports CoreCraft scores in the Inkling 2 Small launch (November 5, 2026): Inkling 2 Small 71.8%, Gemini 3.8 Flash 58.5%, GLM 5.3 51.8%, GLM-5.3-Flash 46.7% and Kimi K3 43.1%.

EnterpriseBench-CoreCraft is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Inkling 2 Small](/models/inkling-2-small) | Thinking Machines Lab | 71.8% |

## FAQ

### What does EnterpriseBench-CoreCraft measure?

An enterprise-operations agent benchmark from Surge AI set in a simulated company (CoreCraft), where agents complete multi-step business tasks across internal tools and records.

### Which model scores highest on EnterpriseBench-CoreCraft?

Inkling 2 Small by Thinking Machines Lab currently leads with a score of 71.8% on EnterpriseBench-CoreCraft.

### How many models are evaluated on EnterpriseBench-CoreCraft?

1 AI models have published results on EnterpriseBench-CoreCraft in the BenchLM catalog.

### Does EnterpriseBench-CoreCraft affect BenchLM's overall score?

Not directly. EnterpriseBench-CoreCraft is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.