Benchmarks · agentic
HANDBOOK.md Agents
Uses Surge AI's first-party MCP-based enterprise policy-following agent score. Score: score. Collected by Jake Boggs' benchmark dashboard.
14 models · 14 results · data as of 2026-10-29 · surgehq.ai ↗
Leaderboard
Opus 5.5 max
All results
14 rows| # | Model | Effort | HANDBOOK.md Agents |
|---|---|---|---|
| 1 | Opus 5.5 | max | 52.3% |
| 2 | Sonnet 5.5 | max | 47.7% |
| 3 | Fable 5.1 | max | 47.1% |
| 4 | Grok 4.7 | xhigh | 44.0% |
| 5 | Gemini 4 Argon | high | 36.6% |
| 6 | Muse Spark 1.3 | max | 33.9% |
| 7 | GPT-6 Astra | max | 31.4% |
| 8 | Qwen 3.8 Max | max | 30.8% |
| 9 | GLM 5.3 | max | 29.9% |
| 10 | Muse Wonder (Max) | max | 29.5% |
| 11 | GPT-6.1 Sol | max | 28.6% |
| 12 | Kimi K3 | max | 28.6% |
| 13 | Gemini 3.8 Flash | high | 26.5% |
| 14 | Hy4 | high | 24.3% |