APEX-Agents-AA — leaderboard
Artificial Analysis implementation of APEX-Agents using the Stirrup agent harness for long-horizon, cross-application professional-services tasks.
Metric: Pass@1 (self-reported). Source: benchmarklist.com. Status: saturation imminent. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 47.1 |
| 2 | GPT-5.5 | 37.7 |
| 3 | GPT-5.4 | 33.3 |
| 4 | Claude Opus 4.6 (Max) | 33 |
| 5 | Gemini 3.1 Pro (Preview) | 32 |
| 6 | GPT-5.4 Mini | 28.2 |
| 7 | Claude Sonnet 4.6 (Max) | 28 |
| 8 | Gemini 3 Flash (Preview) | 27.7 |
| 9 | GPT-5.4 Nano | 24.9 |
| 10 | DeepSeek V4 Pro (Max) | 24.3 |
| 11 | Qwen 3.7 Plus | 22.4 |
| 12 | Grok 4.3 | 17 |
| 13 | Qwen 3.5 397B A17B | 15.3 |
| 14 | DeepSeek V3.2 | 14.5 |
| 15 | GLM-5 | 14.5 |
Interactive version: theaggregate.ai/benchmark?slug=apex-agents-aa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.