Agentic · tools
APEX-Agents leaderboard
As of 2026-10-07, the highest measured score on APEX-Agents is 47.1% by Gemini 3.5 Flash (high).
Measured scores: artificial-analysis.
| # | Model | Score | Source |
|---|---|---|---|
| 1 | Gemini 3.5 Flash (high) | 47.1% | measured |
| 2 | Qwen3.8 Max (0902) | 42.4% | measured |
| 3 | Kimi K3 (max) | 41.3% | measured |
| 4 | GPT-5.6 Terra (max) | 38.9% | measured |
| 5 | Step 5 Preview | 38.0% | measured |
| 6 | GPT-5.5 (xhigh) | 37.7% | measured |
| 7 | GPT-5.6 Luna (max) | 35.8% | measured |
| 8 | GLM-5.2 (max) | 33.7% | measured |
All leaderboards
Agentic · terminal
Agentic · tools
- AA-AnalystAgent
- APEX-Agents
- AutomationBench
- EnterpriseOps-Gym
- Harvey LAB
- ITBench SRE
- τ³-Bench Banking
- τ²-Bench Telecom