Cube vs Jirav
One of fourteen models named Cube first on the direct prompt; zero named Jirav. Cube was named by thirteen of the fourteen models and Jirav by ten and Cube carries 53 labels and Jirav 16, so the shares are not directly comparable.
Named in nine categories this edition.
Named in six categories 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 FP&A platforms page.
By framing
CubeFirst choices, of fourteen modelsJirav
Across every category in the November 2026 Edition, Cube and Jirav were named in the same answer 108 times, of the 352 answers naming Cube and the 166 naming Jirav. In those answers Jirav took the first choice seventeen times and Cube eighteen.
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 4.20 | | | | | ||
| 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 | | | | |
Cube Jirav first choice named as an alternative argued againstblank: not namedEach cell is one answer, Cube on the left and Jirav on the right.The direct prompt
Cube first, Jirav not the choice
1 of 14 modelsJirav was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
5 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
8 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
What the models said about Cube
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of three in this category shown.
“Excel-adjacent tools like Datarails, Cube, and Vena may not be suitable for long-term scalability in large enterprises” Llama 4 Maverick · negative prompt · soft negative
“median pricing for those lands in the $30,000+ range—typically too expensive for "limited budget" teams” Kimi K2 · budget prompt · soft negative
“The best FP&A software for a company with a limited budget is Cube, which offers a free plan and paid plans starting at $40-$80/user/mo.” Llama 4 Maverick · budget prompt · first choice
What the models said about Jirav
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Two of two in this category shown.
“Be careful with "from $50/month" Jirav pricing: the public plans are described as being for FP&A advisory practices” GPT-6 Luna · budget prompt · soft negative
“Jirav is an affordable entry point for small businesses ... making it a relatively cost-effective choice” 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.