Long-Horizon Terminal-Bench leaderboard adds a new agent eval for terminal code tasks
Muennighoff · x · 2026-07-24
A new Long-Horizon Terminal-Bench leaderboard is circulating, ranking 21 entries by pass rate on solved tasks.
The screenshot shows:
- Terminus-2 as the agent stack across the top results.
- Grok 4.5 taking #1, followed by Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5, and GPT-5.6-sol.
- The table is filtered to Solved ≥ 0.95, suggesting the benchmark is focused on high-confidence, long-running terminal tasks.
The post itself is brief, but the image points to another recent eval for measuring how models/agents handle extended code-and-terminal workflows.
More from coding & agent
- Reticle builds a verification layer that lets AI coding agents check their own generated code — Scobleizer · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- Ex-Big Tech managers may thrive in the AI era: manage agents like you managed teams — lxfater · 2026-10-27
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Prompt turns Claude Code into a forensics tool finding deleted iPhone photos in backups — alex_verem · 2026-10-27
- Phones won't be mobile IDEs but control planes for agent fleets, argues Yuchen Jin — Yuchenj_UW · 2026-10-27