Zero of fourteen models named Fireblocks first on the direct prompt; zero named Coinbase Commerce. Fireblocks was named by eleven of the fourteen models and Coinbase Commerce by ten and Fireblocks carries 15 labels and Coinbase Commerce 14, 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 stablecoin platforms page.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | CC | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | CC | |||||
| Grok 4.1 Fast | CC | |||||
| Mistral Small | CC | |||||
| DeepSeek V4 Flash | CC | CC | ||||
| Llama 4 Maverick | CC | CC | ||||
| Qwen 3.7 Flash | CC | |||||
| Kimi K2 | CC | |||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | CC | |||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B | CC |
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. Four of five in this category shown.
“more custody-heavy; overkill unless you need MPC wallets/multi-party security” Grok 4.1 Fast · paraphrase prompt · soft negative
“Circle (USDC) and Fireblocks are both excellent choices” Mistral Small · paraphrase prompt · first choice
“Best if your priority is institutional-grade custody, MPC wallets, and tokenization for your treasury team.” DeepSeek V4 Flash · paraphrase prompt · alternative
“if your top concern is institutional custody, security, and transfer controls” Perplexity Sonar · paraphrase prompt · alternative
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“charge around 1%, and Stripe charges 1.5% plus network fees, which are less cost-effective” Mistral Small · budget prompt · soft negative
“Less ideal for complex B2B workflows (invoicing, batch payouts, multi-currency treasury)” DeepSeek V4 Flash · direct prompt · soft negative
“Coinbase Commerce charges a 1% fee for all crypto payments” Muse Glimmer 30B · budget prompt · soft negative
“the best default choice is usually Coinbase Commerce if you already use Coinbase” Perplexity Sonar · budget prompt · first choice
“Coinbase Commerce is a strong second if you are comfortable holding USDC as an asset.” DeepSeek V4 Flash · budget prompt · alternative
“has 1% fees on stablecoin transactions, with instant settlement to a Coinbase account” Claude Haiku 4.5 · budget 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.