Two of fourteen models named Pulley first on the direct prompt; zero named Shareworks. Pulley was named by fourteen of the fourteen models and Shareworks by thirteen and Pulley carries 66 labels and Shareworks 29, so the shares are not directly comparable.
Named in two categories this edition.
Named in one category this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the cap table management page.
Across every category in the October 2026 Edition, Pulley and Shareworks were named in the same answer seventy-one times, of the 189 answers naming Pulley and the 97 naming Shareworks. In those answers Shareworks took the first choice fifteen times and Pulley thirteen.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Pulley is closing - The platform announced it will cease operations on December 8, 2026 ... If you're considering Pulley, you'll want to evaluate Carta or other alternatives.” MiniMax M2.5 · comparative prompt · hard negative
“Pulley — caution right now because it announced it is shutting down, with final day of operations/services on December 8, 2026.” GPT-5.4 mini · negative prompt · hard negative
“Pulley — avoid for a new setup; migrate if you're already a customer. Pulley has announced it will end operations on December 8, 2026.” GPT-6 Luna · negative prompt · hard negative
“My specific recommendation for most mid-market B2B companies: ... Pulley offers the best balance of capability, price transparency, and ease of use.” DeepSeek V4 Flash · direct prompt · first choice
“Pulley has emerged as the primary challenger to Carta. It is designed specifically for high-growth startups moving through multiple funding rounds.” Qwen 3.7 Flash · comparative prompt · first choice
“Start with Cake Equity or Pulley—both offer the right balance of features” Kimi K2 · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“more appropriately sized than enterprise-first options like Shareworks / Morgan Stanley at Work... Choose Shareworks only if you are already at enterprise complexity” Perplexity Sonar · paraphrase prompt · soft negative
“it's worth a caution for startups specifically ... clunky and overkill for pre-Series-B companies” DeepSeek V4 Flash · negative prompt · soft negative
“If you are an early-stage or mid-stage startup, Shareworks is generally considered a poor fit.” Gemini 3.5 Flash · negative prompt · soft negative
“Shareworks by Morgan Stanley at Work is the mid-market to enterprise benchmark for compliance-oriented administration.” Muse Glimmer 30B · paraphrase prompt · first choice
“The traditional "enterprise" heavyweights. If you are actively on the road to an IPO within the next 12–18 months, these platforms excel ... though they can be slow to implement.” Gemini 3.5 Flash · scale prompt · alternative
“Choose Shareworks if you want a more enterprise/finance-led platform and can tolerate a heavier implementation.” GPT-5.4 mini · direct prompt · alternative
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.