Agentic benchmark
APEX-Agents leaderboard
Every model the catalog carries a published APEX-Agents value for, ranked by that value.
CategoryAgentic
MeasureAgent task-completion score
TasksProfessional-services agent tasks
DifficultyLong-horizon professional work
Published byKimi K3: Open Frontier Intelligence
A professional-services agent benchmark covering long-horizon knowledge-work tasks.
APEX-Agents ranking
9 models with a published APEX-Agents 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 | Agent task-completion score |
|---|---|---|---|
| 1 |  Grok 4.6 | xAI | 57.5 |
| 2 | APApodex 1.1 | Apodex | 38.5 |
| 3 |  Kimi K3 | Moonshot AI | 37.6 |
| 4 |  Hy4 preview | Tencent | 37.1 |
| 5 | DSdots3-note Preview | Dots Studio | 30.8 |
| 6 |  Ling 3.0 Flash Fin | InclusionAI | 29.2 |
| 7 | APApodex 1.1 Mini | Apodex | 27.7 |
| 8 |  Solar Pro 4 | Upstage | 18.7 |
| 9 | Solar Open 2 | Upstage | 16.6 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence 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.