Mercor APEX: leaderboard
Mercor APEX-Agents professional-services benchmark covering long-horizon finance, consulting, and legal workflows in tool-using environments.
Metric: Best Pass@1 (%). Source: www.mercor.com. Saturation forecast: Around January 2027. 53 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 82.4 | #8 |
| 2 | Claude Sonnet 5.5 | 75.5 | #11 |
| 3 | Claude Opus 5.5 | 73.5 | #3 |
| 4 | Claude Fable 5.1 | 68.6 | #9 |
| 5 | Gemini 3.7 Flash | 67.8 | #23 |
| 6 | Claude Opus 5 | 65.8 | #12 |
| 7 | Grok 4.6 | 65.3 | #26 |
| 8 | GPT-6 Astra | 64.7 | #6 |
| 9 | Gemini 3.8 Flash | 64.3 | #21 |
| 10 | Claude Fable 5 | 63.6 | #16 |
| 11 | Qwen 3.8 Max | 63.3 | #35 |
| 12 | GPT-6.1 Sol | 60 | #7 |
| 13 | Muse Spark 1.3 | 58.6 | #24 |
| 14 | GPT-5.6 Terra | 58.2 | #41 |
| 15 | GLM-5.3 | 56.6 | #39 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=mercor-apex · How It Works · Data refreshed daily, snapshot 2026-10-20.