Today for AI
HOT RADAR
agentHEAT 11.7°

AI CURATED HOT STORY · 11/6/2026

SemiAnalysis's GDPx Benchmark Finds Top AI Agents Score Just 12% on Real Work Tasks

1 reports archived1 independent sourcesupdated 11/6/2026, 00:46:24
Synthesis & Latest Updates
1 Sources Cross-Validated

SemiAnalysis has launched GDPx, a benchmark that places AI agents in simulated knowledge-work environments and professional software for multi-hour, 206-task runs, with the best model scoring only 12%. Claude Opus 5.5 leads at 12%, followed by Gemini 4 Carbon at 10.9% and GPT-6 Astra at 9.6%. Critics point to distortions from safety filters, undisclosed tasks, and each provider's own agent tooling, while small per-domain task counts make scores volatile.

LATEST/SemiAnalysis has launched GDPx, a benchmark that places AI agents in simulated knowledge-work environments and professional software for multi-hour, 206-task runs, with the best model scoring only 12%. Claude Opus 5.5 leads at 12%, followed by Gemini 4 Carbon at 10.9% and GPT-6 Astra at 9.6%. Critics point to distortions from safety filters, undisclosed tasks, and each provider's own agent tooling, while small per-domain task counts make scores volatile.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. The DecoderT2·78 pts

    SemiAnalysis's GDPx Benchmark Finds Top AI Agents Score Just 12% on Real Work Tasks

    • GDPx tests agents on 206 tasks inside simulated work environments and professional software, with runs lasting hours rather than knowledge Q&A.
    • The top score of just 12% shows current agents remain far from reliable on long-horizon real workflows.
    • Running each model in its own vendor's agent harness, undisclosed tasks, and safety filters make cross-model comparisons contentious.