Season 1

Tier lists

Clear ranks, dated, with the catch written next to the name. S-tier is locked until our test lab says otherwise.

What OP or Mid's ranks mean, as of October 15, 2026. S-tier is locked until a hands-on test earns it.
Rank	Meaning	How you get there
S	Best in our hands-on tests.	Locked until the test lab says so. Nobody has it yet.
A	A strong default this week.	Good enough to be the main pick, with the catch written beside it.
B	Good, with a real catch.	Competitive, but unproven, pricey, or missing something that matters.
C	Held back.	Usable, but a bug, a price trap, or an open security issue is in the way.
D	Hard to recommend.	Serious problems, and no reason to start here.
F	Avoid.	A product or a playstyle that will waste the week.

PreliminaryUpdated October 15, 2026
AI Coding Agents
As of October 15, 2026, OP or Mid's AI coding-agent tier list is preliminary. S-tier is locked until a tool earns it in hands-on tests, which start in Issue #2. A-tier this week is Codex (GPT-6.1 Sol), Claude Code (Claude 5.5 family), Antigravity with Gemini 4 Argon, and Cursor. Muse Code is B-tier. Continue CLI is C-tier because CVE-2026-109560 has no listed fix. These placements come from official changelogs, published pricing, and vendor-reported benchmarks, not from OP or Mid's own test lab.
Open the board
PreliminaryUpdated October 15, 2026
Frontier Models
As of October 15, 2026, OP or Mid's frontier-model list is preliminary. S-tier is locked. Gemini 4 Argon, GPT-6, and the Claude 5.5 family are A-tier on changelogs and published pricing, not on a hands-on bake-off. Muse Wonder is B-tier because it is three days old and Wonder Full has no API. Vendor benchmark claims are labeled and unverified.
Open the board

AI Coding Agents