Forma vs JOON
Four of fourteen models named Forma first on the direct prompt; zero named JOON. Forma was named by fourteen of the fourteen models and JOON by ten and Forma carries 51 labels and JOON 13, so the shares are not directly comparable.
Named in three 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 flexible benefits and lifestyle spending accounts page.
By framing
FormaFirst choices, of fourteen modelsJOON
Across every category in the October 2026 Edition, Forma and JOON were named in the same answer twenty-two times, of the 184 answers naming Forma and the 36 naming JOON. In those answers JOON took the first choice seven times and Forma seven.
Every model, every framing
| 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 | | |
Forma JOON first choice named as an alternative argued againstblank: not namedEach cell is one answer, Forma on the left and JOON on the right.The direct prompt
Forma first, JOON not the choice
4 of 14 modelsJOON was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
6 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
4 of 14 modelsThe answer made no first choice from these two in this category.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.
By buyer segment
Forma16%#3 of 10JOON8%#4 of 10What the models said about Forma
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of six in this category shown.
“Forma has user reviews reporting limited information and reimbursement delays, with regular support gaps rounding out top complaints” Claude Haiku 4.5 · negative prompt · hard negative
“3. Forma ... Users describe it as one of the "worst experiences" to use” GLM 4.7 FlashX · negative prompt · hard negative
“Caution: Higher implementation fees (~$10,000+) and generally higher pricing... May be overkill for leaner mid-sized teams.” Kimi K2 · paraphrase prompt · soft negative
“Differentiator: It's the most comprehensive "one-stop-shop" — handling both pre-tax and post-tax benefits with the broadest global footprint.” DeepSeek V4 Flash · comparative prompt · first choice
“Some platforms, like Forma, offer a streamlined approach to managing pre-tax and post-tax benefits under a single, intuitive platform” Llama 4 Maverick · comparative prompt · first choice
“Forma helps companies manage flexible benefits at scale by consolidating employee perks and benefits into a single platform.” Claude Haiku 4.5 · comparative prompt · first choice
What the models said about JOON
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“For a small or budget-conscious U.S. company, I'd start with JOON if you want a standalone, flexible LSA platform with public entry-level pricing.” GPT-6 Luna · budget prompt · first choice
“For the tightest budget: Start with Joon or Compt at $250/month” Kimi K2 · budget prompt · first choice
“Joon appears to be the top choice for smaller companies.” Claude Haiku 4.5 · budget prompt · first choice
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.