🤖 Agentic · source: llm-stats.com
Apex Agents
Long-horizon professional agent tasks with multi-app workflows.
4
Models Tested
Kimi K3
Top Model
37.6%
Top Score
Moonshot AI
Provider
| # | Model | Apex Agents |
|---|---|---|
| 1 | Kimi K3 Moonshot AI | 37.6% |
| 2 | Gemini 3.1 Pro Google | 33.5% |
| 3 | Kimi K2.6 Moonshot AI | 27.9% |
| 4 | Hunyuan Hy3 Tencent | 25.6% |
Benchmark data aggregated from llm-stats.com. See Methodology for details.