AgentS4D - Task Completion (Claude Code): leaderboard

Metric: Task completion rate (%): runs whose case-specific completion predicate for the authorized task is satisfied, over the 328 risk-injected cases run once in the Claude Code (2.1.201) harness; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1GPT-5.597.87
2DeepSeek V4 Pro94.51
3MiniMax-M394.51
4Gemini 3.1 Pro (Preview)89.33
5Qwen 3.7 Plus87.5

Interactive version: theaggregate.ai/benchmark?slug=agents4d-task-completion-claude-code · How It Works · Data refreshed daily, snapshot 2026-09-29.