GDPx v1.0 - Cybersecurity - Arithmetic - Default Score: leaderboard
GDPx v1.0 Cybersecurity - Arithmetic - Default Score measures professional agent work using the publisher's native task-specific scores on a 0–100 scale. Three attempts are run per task, normally with an eight-hour limit. Scores mix binary and continuous grading; the overall mean weights eleven domains equally and partners equally within each domain. Native harness, effort and assigned/scored counts remain separate; missing native scores are not treated as zero.
Metric: Default Score (%). Source: gdpx.semianalysis.com. Saturation forecast: Rough model projection: around 2026. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Wonder Full (GDPx Run: v1.0; muse-wonder-full; Muse Code; effort Highest) | 35.19 | |
| 2 | Muse Wonder (GDPx Run: v1.0; muse-wonder; Muse Code; effort Highest) | 24.07 | |
| 3 | Gemini 4 Argon (GDPx Run: v1.0; gemini-4-argon; Antigravity; effort High) | 18.52 | |
| 4 | DeepSeek V4.1 Flash (1017) (GDPx Run: v1.0; deepseek-4-1-flash; DeepSeek Harness; effort Highest) | 16.67 | |
| 5 | Gemini 4 Carbon (GDPx Run: v1.0; gemini-4-carbon; Antigravity; effort High) | 16.67 | |
| 6 | Grok 4.7 (GDPx Run: v1.0; grok-4-7; Grok Build; effort xHigh) | 14.81 | |
| 7 | GPT-6 Luna (GDPx Run: v1.0; gpt-6-luna; Codex; effort Max) | 11.11 | |
| 8 | Kimi K3 (GDPx Run: v1.0; kimi-k3; Kimi Code; effort Highest) | 11.11 | |
| 9 | Claude Haiku 5.5 (GDPx Run: v1.0; claude-haiku-5-5; Claude Code; effort Max) | 9.26 | |
| 10 | Claude Opus 5.5 (GDPx Run: v1.0; claude-opus-5-5; Claude Code; effort Max) | 9.26 |
Interactive version: theaggregate.ai/benchmark?slug=gdpx-v1-0-cybersecurity-arithmetic-default-score · How It Works · Data refreshed daily, snapshot 2026-11-05.