HANDBOOK.md Agents: leaderboard
Surge AI long-context agentic instruction-following benchmark in which an agent must apply a 100-page company handbook inside a unique RL environment with internal tools and external MCP servers, across five enterprise domains.
Metric: Score (%). Source: surgehq.ai. Saturation forecast: Around 2030. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | 47.1 | #9 (Claude Fable 5.1) |
| 2 | Grok 4.7 (xHigh) | 44 | #25 (Grok 4.7) |
| 3 | Gemini 4 Argon (High) | 36.6 | #8 (Gemini 4 Argon) |
| 4 | Muse Spark 1.3 (Max) | 33.9 | #24 (Muse Spark 1.3) |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=handbook-md-agents · How It Works · Data refreshed daily, snapshot 2026-10-20.