한국어EN
Evaluation & BenchmarksLaude Institute

Laude Institute releases Terminal-Bench 2.1

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Released Terminal-Bench 2.1 — fixed 28 tasks because of changes in external dependencies, resource mismatches and specification errors

Why it matters

A case of a benchmark publicly admitting its own defects and introducing an ongoing checking process

Source — Primary sources first; secondary reports are labelled “Press”

Officialtbench.aihttps://www.tbench.ai/news/terminal-bench-2-1

Added in Week 35, 2026 · See that week

On the map — ⑯ Evaluation line

  1. Previous stopARC-AGI-3
  2. This recordTerminal-Bench 2.1
  3. Next stopRealSWE
See it on the map

Same week

Iwase et al. publish Reliable Chain-of-Thought via Prefix ConsistencyPaperTeaching Claude WhyOfficialStop Comparing LLM Agents Without Disclosing the HarnessPaperGPT-Realtime-2 / -Translate / -WhisperOfficial

Nearby on the same axis

Liu et al. release ABC-BenchPaperEpoch AI releases a revised FrontierMathOfficialARC Prize releases ARC-AGI-3OfficialBioSecBench-Refusal releasedPaper