SysTradeBench - Audit Gate: leaderboard
Metric: Audit gate pass rate (%): share of the 12 strategies whose submission produces complete mandatory audit logs (signal, risk check, order, position and P&L trace), the last and strictest of six validity gates applied in order to each zero-shot (Iter0, temperature 0) submission of strategy card, executable code and audit log for 12 standardized trading-strategy specifications: parse, schema, execution, determinism, anti-leakage and audit; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 100 |
| 2 | GPT-5.1 | 100 |
| 3 | O3 | 100 |
| 4 | GLM-4.6 | 91.7 |
| 5 | Grok 4 Fast | 91.7 |
| 6 | Claude Sonnet 4.5 | 83.3 |
| 7 | Grok 3 | 83.3 |
| 8 | Grok 4.1 Fast (Reasoning) | 83.3 |
| 9 | Grok Code Fast 1 | 83.3 |
| 10 | Claude Opus 4.5 | 75 |
| 11 | Gemini 3 Pro | 66.7 |
| 12 | GLM-4.7 | 50 |
| 13 | Gemini 2.5 Pro | 33.3 |
| 14 | Gemini 3 Flash | 33.3 |
| 15 | Grok 4 | 25 |
Interactive version: theaggregate.ai/benchmark?slug=systradebench-audit-gate · How It Works · Data refreshed daily, snapshot 2026-10-07.