Agentic benchmark
ApprenticeBench leaderboard
ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job. Every model the catalog carries a published ApprenticeBench value for, ranked by that value.
Tests whether a computer-use agent can learn a real accounts-payable job on the job, processing 100 vendor bills in a company ERP system with only the handbook, historical records, and mentor feedback a new hire would get.
ApprenticeBench ranking
18 models with a published ApprenticeBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Cumulative success rate over 100 bills |
|---|---|---|---|
| 1 |  Claude Fable 5.1 | Anthropic | 72 |
| 2 |  GPT-6 Astra | OpenAI | 68 |
| 3 | Claude Opus 5 | Anthropic | 36 |
| 4 | Claude Fable 5 | Anthropic | 34 |
| 5 | GPT-5.6 Sol | OpenAI | 26 |
| 6 |  Gemini 3.8 Flash | 24 | |
| 7 | GPT-5.5 | OpenAI | 20 |
| 8 |  Muse Spark 1.3 | Meta | 19 |
| 9 |  Kimi K3 | Moonshot AI | 18 |
| 10 | Claude Sonnet 5 | Anthropic | 16 |
| 10 | Gemini 3.7 Flash | 16 | |
| 10 | GPT-5.6 Terra | OpenAI | 16 |
| 13 |  Grok 4.6 | xAI | 13 |
| 14 | GPT-5.4 | OpenAI | 11 |
| 15 | Claude Opus 4.7 | Anthropic | 7 |
| 15 | GPT-5.6 Luna | OpenAI | 7 |
| 17 | Claude Opus 4.6 | Anthropic | 5 |
| 18 | Claude Sonnet 4.6 | Anthropic | 2 |
Evidence key: Observed
Rows are ordered by the value ApprenticeBench: a step change in AI's job readiness published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.