Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-02-23 · source-backed
Arena Mode is the standout. Run two agents on the same prompt with hidden model identities, vote on which performs better. 40K+ votes so far. Key finding from the community leaderboard: speed beats intelligence in most real-world tasks (Gemini 3 Flash beats Gemini 3 Pro). Plan Mode creates structured plans before executing. Parallel Agents with Git Worktrees spawn multiple sessions in the same repo without conflicts.
SWE-1.5 is free through March 2026 — 950 tokens/sec (13x faster than Claude Sonnet 4.5) while achieving 40.08% on SWE-Bench Pro. Try Arena Mode this week to discover which model actually works best for YOUR codebase and task types.
Source: Windsurf Blog | Windsurf Arena Leaderboard
Each link below shares sources, entities, or timing with this story.
Gemini built by Google / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Gemini built by Google); both cover Bench Pro, Flash, Gemini, March; overlapping topics (beat, gemini).
Codex competes with Gemini / Shared entities / Same source domain / Shared topic / What happened next
Linked by a graph relationship (Codex competes with Gemini); both cover Arena Mode, Git Worktrees, Plan Mode, SWE; reported by the same outlet (windsurf.com).
Cursor supports Gemini / Shared entities / Same source / Shared topic
Linked by a graph relationship (Cursor supports Gemini); both cover Arena Mode, Plan Mode, SWE, Windsurf Blog; cite the same source (Windsurf Blog).
Codex competes with Gemini / Shared entities / Shared topic
Linked by a graph relationship (Codex competes with Gemini); both cover Arena Mode, Gemini, Plan Mode, SWE; overlapping topics (agent, arena, claude, mode).
Gemini competes with ChatGPT / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Gemini competes with ChatGPT); both cover Bench Pro, Flash, Gemini, SWE; overlapping topics (model, task).
Shared entities / Same source / Shared topic / What happened next
Both cover Arena Mode, Claude Sonnet, Plan Mode, SWE; cite the same source (Windsurf Blog); overlapping topics (agent, arena, claude, mode, model).
Cursor supports Gemini / Shared entities / Shared topic / What happened next
Linked by a graph relationship (Cursor supports Gemini); both cover Arena Mode, Gemini, SWE; overlapping topics (agent, arena, claude, model).
Copilot deprecates Gemini / Shared entities / Shared topic / What happened next / Tension
Linked by a graph relationship (Copilot deprecates Gemini); both cover Bench Pro, Flash, SWE; overlapping topics (beat, model).