AINewsnow

Two independent audits of Terminal Bench 4: 41 of 65, or 30 of 66?

Epoch AI published a benchmark review of Terminal-Bench 4.0.0 and gave it the verdict Flawed: 30 of 66 tasks (45.5%) carry publicly documented scoring defects. Separately, Preference Model ran its own audit of the same benchmark and reported that in 41 of the 65 tasks they ported, a model could do…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-03 14:15 · DEV Community — AI
    Two independent audits of Terminal Bench 4: 41 of 65, or 30 of 66?

More stories

  1. OpenAI Hires Former Army Secretary Dan Driscoll as Senior Counselor for National Security — OpenAI News
  2. Security flaw found in Claude Code extension listed on Cursor's marketplace — Runway Research
  3. OpenAI raises bug bounty rewards and plans new security sprint with outside researchers — OpenAI News
  4. OpenAI seeks to rebrand data centers as 'compute campuses' amid growing local backlash — Techmeme
  5. Anthropic launches Message Threads in public beta, cutting agent request payloads from 800 KB to 1.8 KB — Anthropic (X)
  6. UK cyber agency warns AI-powered malware likely to hit critical infrastructure by 2028 — The Guardian AI
  7. Marvell to Acquire Lumentum in $115 Billion All-Stock AI Optics Deal — DigiTimes Asia
  8. Sam Altman visits Samsung and SK in South Korea amid deepening memory chip shortage — Bloomberg AI

Get the daily brief of stories like this at 6:30 every morning →