Home Model series GPT Codex GPT-5.1 Codex-Max GPT-5.1 Codex-Max · Terminal-Bench · 2.0;代理框架按协议区分 · Scores and configurations GPT-5.1 Codex-Max · Terminal-Bench · 2.0;代理框架按协议区分 · Scores and configurations GPT-5.1 Codex-Max record for Terminal-Bench · 2.0;代理框架按协议区分. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5.1 Codex-Max · Terminal-Bench scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 58.1% Reported 58.1% · Unit % Published 2025-11-19
GPT-5.1 Codex-Max (xhigh) Settings Extra-high reasoning and compaction; Terminal-Bench 2.0 run through Codex CLI in Harbor. Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework Codex CLI in the Laude Institute Harbor harness Protocol Terminal-Bench 2.0 via Codex CLI in Harbor harness. Conditions Compaction enabled; xhigh reasoning effort. View this score in rankings
Benchmark versions and metrics Aliases Terminal-Bench 2.0
Pass rate · % · Higher is better Mean reward · % · Higher is better