Checked Sep 5, 2026 30 tools · 100 models · ranked and tracked separated 3 changes in this edition →
EDITION 2026.09 / EDITORIAL EVIDENCE INDEX
Tools are the products you work in — builders, agentic IDEs, design-to-code. Models are the engines underneath them. They are scored in two separate contests, because a workflow and a foundation model are not the same unit.
Editorial evidence score, not a lab benchmark. No hands-on build was performed. How scoring works →
Twelve seconds. Then everything else on the page makes sense.
5 QUESTIONS / NO ACCOUNT
Answer five plain questions. The finder transparently re-weights the published evidence model and returns exactly three options, each with a reason and a tradeoff.
Pick an answer to the first question to see recommendations.
PERSONAL RANKING LENSES
Each lens re-weights the same published subscores. The board shows which dimensions gained weight and how every leader moved from the balanced ranking.
Balances visual quality, engineering depth, speed, control, ecosystem, delivery, and value.
USER MOMENTUM LEADER
49.665 trillion tokens and 500.5 million requests. Hermes is also #2 on the day, week, and coding-category views. That is extraordinary verified usage, not a claim that it has the best visual output.
Trailing windows, not downloads, stars, or survey opinions.
Products not routed through OpenRouter are marked not measured, never zero.
Future ratings will shrink small samples toward the catalogue mean and decay stale activity.
Public ranks can contain gaps because hidden and private apps are excluded. We publish the source rank as-is and never densify it. OpenRouter apps ↗ Ranking definition ↗ Bayesian method ↗
TOOLS LANE / PRODUCT EVIDENCE MODEL
20 ranked tools shown
| Rank | Tool | Score | Dimension profile | Why it ranks here | Price / free tier | Code export | Best for | Conf. | Compare |
|---|
These entries are in the index and searchable, but the rubric evidence needed for an ordinal rank does not exist yet. No score is invented, and published ranks are untouched.
Ranked entries are commercial or open products with first-party frontend evidence. Terminal-only agents, spec-driven PR bots, and brand-new releases enter as tracked entries first. Nominate a missing tool by opening an issue against the published method.
INTERACTIVE MODEL
Change what matters and the board re-ranks instantly. The model stays constrained to 100%, and the preset is written into the URL so you can share the exact view you are looking at.
Overall = Σ (subscore × dimension weight ÷ 100)
Whole-number subscores; overall rounded to one decimal. Other sliders normalise proportionally when one changes. Published ranks always use the Balanced preset.
CATEGORY LENS
Different jobs, different winners. Category context prevents false equivalence.
MODEL RANKING LENSES
The Quality / Cost lens prices a standard coding task, applies a nonlinear anti-junk gate, and reports value logarithmically so +10 points means 10× better value.
QUALITY / COST FRONTIER
Up is better. Left is cheaper. The models on the glowing edge deliver quality that cheaper rivals cannot match within the evidence tolerance.
Calculating the current quality premium…
100 UNDERLYING MODELS / 30 EVIDENCE-RANKED
Loading 100 models…
These models complete the Top 100 catalogue. They have verified availability metadata, but no ordinal quality rank until benchmark evidence is normalized across comparable harnesses.
CATALOGUE / NOT A COMMON RANKING
Tools and models are grouped by type. Each score is shown only inside its own evidence model.
A product workflow and an underlying foundation model are different units. Combining them would create false precision, so the catalogue keeps them apart and labels the type on every card.
DECISION WORKSPACE
Search and swap up to three entries. Winners, meaningful differences, and the recommended choice are calculated from the active lens and saved in the URL.
WHAT CHANGED / EDITION 2026.09
Every edition states what moved and why. Subscribe with the Atom feed.
EDITION HISTORY
30 tools and 100 models. Entries are labelled New, Updated evidence, Price changed, Tracked, or No prior snapshot. Rank deltas begin only after a comparable numeric snapshot exists.
No rank movement is claimed for this edition.
METHOD / SOURCE QUALITY
The index uses separate evidence models for products and foundation models. Type is always visible because tools and models are not comparable units.
0.20·VF + 0.20·ED + 0.15·SP + 0.15·IT + 0.10·EC + 0.10·DP + 0.10·VP
Subscores are whole numbers from 0–100. Weighted overall scores are rounded to one decimal.
Quality = 0.25·VI + 0.20·CO + 0.15·AG + 0.10·DE + 0.10·CT + 0.10·SP + 0.10·VA
Quality / Cost prices 1M input tokens at a 70% cache-hit share plus 200K output, applies a confidence-adjusted logistic quality gate, and reports quality-adjusted cost in decibels. +10 points means 10× better value.
Official product, pricing, and documentation pages first; primary financial disclosures second; credible reporting and independent hands-on evaluations for corroboration and limitations.
An entry is TRACKED when it is real and relevant but lacks the frontend-specific evidence the rubric requires. Tracked entries get no ordinal rank, no invented subscores, and are excluded from every ranked count.
Missing facts stay n.a.; conflicts stay visible. Corrections are welcome and are logged in the next edition's Updates section.
EVIDENCE CARD
SIDE-BY-SIDE
COMPARISON ALREADY OPEN