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 3.6 Flash launched July 21 at $1.50/1M in, $7.50/1M out, claiming 17% fewer output tokens than 3.5 Flash, DeepSWE code precision up from 37% to 49%, OSWorld-Verified computer use at 83% (from 78.4%), and a knowledge cutoff finally moved from January 2025 to March 2026....
Windsurf's Wave 13 makes SWE-1.5 free for all users for 3 months (full SWE-Bench-Pro performance). Five concurrent parallel Cascade agents via git worktrees. Arena Mode for blind A/B comparison with voting. Plan Mode as pre-implementation planning. GPT-5.2-Codex support with f...
Windsurf Wave 13 took #1 in the LogRocket Power Rankings with Arena Mode (A/B test models on your codebase), Plan Mode, and 5 parallel agents in Git worktrees at $15/mo. Cursor 2.0 counters with 8 parallel agents, async subagent trees, and Composer at 4x speed. Kimi K2.5 crash...
The LogRocket February 2026 Power Rankings reshuffled: | Rank | Tool | Price | Key Feature | |------|------|-------|-------------| | 1 | Windsurf | $15/mo | Arena Mode + parallel worktrees | | 2 | Antigravity (Google) | Free-$250 | Deep Google ecosystem integration | | 3 | Cur...
OpenAI shipped the first model family explicitly designed for subagent pipelines. GPT-5.4 mini features a 400K context window, scores 54.4% on SWE-Bench Pro (vs. the flagship's 57.7%), and handles computer use at 72.1% on OSWorld — at $0.75 input / $4.50 output per million tok...
Windsurf Wave 13 claims the #1 AI IDE ranking with Arena Mode (blind side-by-side model comparison, 40K+ votes), Plan Mode (step-by-step before code generation), and parallel agents via git worktrees. SWE-1.5 Free runs at 950 tok/s. Claude Sonnet 4.6 added with promotional pri...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.