Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-02-24 · source-backed
The February rankings reshuffled: Windsurf #1 (Arena Mode for side-by-side model comparison), Antigravity (Google) #2, Cursor #3 (8 async subagents + Multi-Agent Judging), Kimi Code NEW at #4 — the first open-source tool in the top 5 with 100-agent swarm capability backed by Kimi K2.5 (76.8% SWE-bench), and Claude Code #5 with CLI depth and native worktree isolation.
The three-tool workflow crystallizes: Cursor for in-editor velocity, Claude Code for planning/architecture/CLI, Windsurf for model comparison. The frontier coding models (Opus 4.6 80.8%, GPT-5.3-Codex 80.0%, Gemini 3.1 Pro 80.6%) are in a statistical tie on SWE-bench — tool choice now matters more than model choice.
Each link below shares sources, entities, or timing with this story.
Codex competes with Claude Code / Shared entities / Same source / Shared topic / Earlier coverage
Linked by a graph relationship (Codex competes with Claude Code); both cover Antigravity, Arena Mode, Claude Code, CLI; cite the same source (February rankings).
Cursor benchmarked against Codex / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Cursor benchmarked against Codex); both cover Antigravity, Claude Code, Codex, Cursor; overlapping topics (agent, architecture, code, model).
Cursor benchmarked against Codex / Shared entities / Same source / Shared topic / Earlier coverage
Linked by a graph relationship (Cursor benchmarked against Codex); both cover Arena Mode, Cursor, Kimi K2, SWE; cite the same source (February rankings).
Cursor benchmarked against Codex / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Cursor benchmarked against Codex); both cover Antigravity, Claude Code, CLI, Cursor; overlapping topics (agent, architecture, claude, code, model).
Linked by a graph relationship (Cursor benchmarked against Codex); both cover Claude Code, Cursor, Google, GPT; overlapping topics (agent, code, cursor, model).
Copilot uses GPT / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Copilot uses GPT); both cover Antigravity, Claude Code, CLI, Cursor; overlapping topics (agent, claude, code, tool).
Copilot uses GPT / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Copilot uses GPT); both cover Antigravity, Claude Code, Codex, Cursor; overlapping topics (agent, antigravity, architecture, claude, code).
Codex competes with Gemini / Shared entities / Shared topic / Downstream implication
Linked by a graph relationship (Codex competes with Gemini); both cover Codex, Gemini, GPT, Kimi K2; overlapping topics (kimi, model, swe-bench).