# Cube vs Abacum: which do AI models recommend for cash flow forecasting, September 2026

Finance AI Recommendation Index, September 2026 Edition, Cash flow forecasting. Two of twelve models named Cube first on the direct prompt; two named Abacum. Page: https://finance-ai-index.com/treasury/cash-flow-forecasting/cube-vs-abacum/

| | First-choice share | Rank | Negative rate | Labels | Models naming it |
|---|---|---|---|---|---|
| Cube | 4% | #4 of 14 | 0% | 24 | 12 of 12 |
| Abacum | 4% | #6 of 14 | 6% | 17 | 11 of 12 |

## The direct prompt, model by model

- Mistral Small: cube first (first choices: Cube) (alternatives: Abacum, Chaser)
- Llama 4 Maverick: cube first (first choices: Cube) (alternatives: Abacum, Agicap, Chaser, GTreasury)
- Perplexity Sonar: abacum first (first choices: Abacum, Drivetrain) (alternatives: Chaser, Cube, Vena)
- DeepSeek V4 Flash: abacum first (first choices: Abacum) (alternatives: Centime, Chaser, Cube, Drivetrain)
- Claude Haiku 4.5: neither first, one named (first choices: Tesorio) (alternatives: Billtrust, Cube, Drivetrain)
- GPT-5.4 mini: neither first, one named (first choices: Agicap) (alternatives: Cube, Float, Tesorio)
- Gemini 3.5 Flash: neither first, one named (first choices: Centime, Tesorio) (alternatives: Agicap, Cube, Mosaic, Trovata)
- Grok 4.1 Fast: neither first, one named (first choices: Chaser, Drivetrain) (alternatives: Abacum, Upflow)
- Qwen 3.7 Flash: neither first, one named (first choices: Chaser) (alternatives: Abacum, Phocas Software, Vena)
- Kimi K2: neither first, one named (first choices: Tesorio) (alternatives: Agicap, Chaser, Cube, Float)
- GLM 4.7 FlashX: neither first, one named (first choices: Chaser) (alternatives: Abacum, Drivetrain, Float, Futrli, Upflow)
- MiniMax M2.5: neither first, one named (first choices: Chaser) (alternatives: Cube, Tesorio)

## What the models said about Cube

- "If your team relies on spreadsheets but wants to improve forecasting, Cube is a top choice." (Mistral Small, direct prompt, first choice)

## What the models said about Abacum

- "Abacum (not for enterprises)" (Grok 4.1 Fast, negative prompt, soft negative)
- "Best overall for mid-market FP&A and scenario planning: Abacum" (Perplexity Sonar, direct prompt, first choice)
- "Abacum — Best overall for mid-market FP&A teams" (DeepSeek V4 Flash, direct prompt, first choice)

Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve models, for a mid-market B2B company; rank is within the category. Comparisons are drawn for the top eight products in each category. Published under CC BY 4.0; the output is the models' output, and nothing here is a recommendation by the index.