LLM Stats (APEX-Agents): leaderboard
LLM Stats mirror of the APEX-Agents benchmark, measuring autonomous agent performance on realistic professional-services workflows.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around August 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 60 | #7 |
| 2 | Grok 4.6 | 57.5 | #26 |
| 3 | Kimi K3 | 37.6 | #30 |
| 4 | Hy4 preview | 37.1 | #38 |
| 5 | Seed 2.1 Pro | 33.8 | #67 |
| 6 | Gemini 3.1 Pro (Preview) | 33.5 | #58 |
| 7 | Seed 2.1 Turbo | 29.2 | #86 |
| 8 | Ling-3.0-flash-fin | 29.17 | #108 |
| 9 | Kimi K2.6 | 27.9 | #104 |
| 10 | MiniMax-M3 | 27.7 | #136 |
| 11 | Hy3 | 25.6 | #93 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-apex-agents · How It Works · Data refreshed daily, snapshot 2026-10-20.