Rohan Paul@rohanpaul_ai

2026-07-24 01:39· 1天前

AI 摘要

Offloop 的 4 人团队用多智能体系统在 GDPval 基准上以每任务 $1.65 的成本取得 84.9 分，超越 Claude Code（82.4 分，$14.38/任务）和 Codex（83.3 分，$5.20/任务）。该系统还在 GDP.pdf 和 JobBench 上达到 SOTA，成本仅为竞品的 1/3 到 1/10。

So much recent work and research papers points to the same thing： the "harness" is becoming the real capability layer.

@Offloop 's 4-person team demonstrated a multi-agent harness outperforming Claude Code and Codex on GDPval benchmarks， targeting $2.4T in US knowledge work.

The team scored 84.9 at $1.65 per task.
Opus 4.8 inside Claude Code scored 82.4， and GPT 5.6 Sol inside Codex scored 83.3， costing far more per task， $14.38 and $5.20

GDPval measures how well AI handles real work across 44 occupations and 9 major industries. Models get shell access and web browsing， then face blind pairwise comparisons against human experts.

And those tasks map onto US jobs paying roughly $2.4T a year.

OffloopIn our internal evaluations, Offloop achieved new state of the art results on three benchmarks evaluating professional knowledge work: 84.9 on GDPval, 44 on GDP...

智能体 Anthropic OpenAI

Rohan Paul@rohanpaul_ai · X

42导出 Markdown

2026-07-24 01:39·1天前

在 X 看原推· x.com

AI 摘要

So much recent work and research papers points to the same thing： the "harness" is becoming the real capability layer.

@Offloop 's 4-person team demonstrated a multi-agent harness outperforming Claude Code and Codex on GDPval benchmarks， targeting $2.4T in US knowledge work.

The team scored 84.9 at $1.65 per task.
Opus 4.8 inside Claude Code scored 82.4， and GPT 5.6 Sol inside Codex scored 83.3， costing far more per task， $14.38 and $5.20

GDPval measures how well AI handles real work across 44 occupations and 9 major industries. Models get shell access and web browsing， then face blind pairwise comparisons against human experts.