Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-07-14 · high
GPT-5.6 Sol Ultra scored highest overall at 91.9%, outside the roughly 35-agent CLI field Morph ranks as of the July 14 standings.
Why now: The July 14 standings give teams a fixed reference instead of re-litigating CLI choice after every model release.
Codex CLI running GPT-5.5 leads the public Terminal-Bench 2.1 leaderboard at 83.4% in the July 14 standings, per Morph.
That's the number worth citing when a team argues over which coding CLI to standardize on. Morph counts roughly 35 actively maintained CLI agents in the same field as of July 14.
GPT-5.6 Sol Ultra scored highest overall at 91.9%, but that sits outside the public CLI-pairing leaderboard Codex CLI leads.
Claude Code paired with Opus 4.8 is the top usable Claude pairing at 78.9%, about 4.5 points behind Codex CLI. Gemini CLI with Gemini 3.1 Pro trails both at 70.7%.
Opencode is the most-starred option among that open-source field, per Morph.
Morph doesn't say what disqualifies a Claude pairing from the top spot, or how excluded configurations scored. So 78.9% is a floor for Claude Code, not the full range of what's possible with it.
A 4.5-point Terminal-Bench gap between Codex CLI and Claude Code is a tiebreaker for whoever's picking cold, not a verdict on whoever's already shipping. If Codex CLI's lead holds through the next model drop for Claude Code, that's the signal worth switching over. Until then, the standings are a reference for new decisions, not grounds to relitigate old ones.
The July 14 standings give teams something fixed to point to instead of restarting the CLI argument after every model release.
Each link below shares sources, entities, or timing with this story.
Claude Code uses Opus / Shared entities / Same source domain / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code uses Opus); both cover Bench, Claude, Claude Code, Codex CLI; reported by the same outlet (morphllm.com).
OpenCode competes with Claude Code / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (OpenCode competes with Claude Code); both cover Bench, CLI, Codex CLI, Gemini CLI; reported by the same outlet (morphllm.com).
Windsurf uses Claude Code / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Windsurf uses Claude Code); both cover Claude, Claude Code, CLI, Codex CLI; overlapping topics (agent, claude, code, codex, gemini).
Claude Code uses Sonnet / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Sonnet); both cover Claude, Claude Code, Gemini, GPT; overlapping topics (agent, claude, code, codex, coding).
Codex competes with Claude Code / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Codex competes with Claude Code); both cover Bench, CLAUDE, Claude Code, GPT; overlapping topics (claude, code, coding).
Claude Code uses Opus / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Bench, Gemini, GPT, Opus; overlapping topics (agent, code, coding).
Windsurf uses Claude Code / Shared entities / Shared topic / Earlier coverage
Linked by a graph relationship (Windsurf uses Claude Code); both cover Claude Code, CLI, Gemini, GPT; overlapping topics (agent, claude, code).
Claude Code uses MCP / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code uses MCP); both cover Claude, Claude Code, Gemini, Opus; overlapping topics (agent, claude, code, coding).