HOT RADAR
agentHEAT 13.8°

AI CURATED HOT STORY · 11/18/2026

SWE-CoWork Benchmark Exposes Coding Agents' 8% Task Completion Rate

1 reports archived1 independent sourcesupdated 11/18/2026, 00:37:08
Synthesis & Latest Updates
1 Sources Cross-Validated

TokenWave AI has released SWE-CoWork, a benchmark that places coding agents in a simulated workplace where 82% of requirements live with teammates, forcing agents to ask the right person to learn what to build. Across 101 tasks drawn from real open-source repositories, the best models pass roughly 63% of individual checks but fully complete only 8 of 101, exposing long-horizon collaboration and information gathering as core weaknesses.

LATEST/TokenWave AI has released SWE-CoWork, a benchmark that places coding agents in a simulated workplace where 82% of requirements live with teammates, forcing agents to ask the right person to learn what to build. Across 101 tasks drawn from real open-source repositories, the best models pass roughly 63% of individual checks but fully complete only 8 of 101, exposing long-horizon collaboration and information gathering as core weaknesses.

Hourly heat curve

6 fully observed hours
Now
13.8
Peak
15.601:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. Rohan Paul (@rohanpaul_ai)T2·78 pts
    • 82% of requirements sit with simulated teammates, so agents must actively communicate to scope work, testing information gathering rather than pure coding
    • Top models pass about 63% of individual checks but fully finish fewer than 8 of 101 tasks, making end-to-end completion the main bottleneck
    • The benchmark spans 101 real open-source repositories, 26 simulated teammates, 11 languages, 12 domains and 17 workplace tools