Index › Finance › Accounting and close › AI accounting assistants › Small business · November 2026 Edition
AI accounting assistants for small business buyers
Asked as “AI bookkeeping tool”, and as “AI agent for accounting tasks”, on behalf of a small B2B company. 51 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
24%
Contested · Digits 12%
24QuickBooks Online12Digits12Xero53others
24% of first choices, contested.
Since October 2026▼−18Since October 2026: 42% → 24%, −18 points. Past the 10-point floor: movement.QuickBooks Online held the lead, −18 points on 42%, past the floor.
By buyer segment
The same question asked on behalf of a different buyer. Each standing is computed within its segment; they sit side by side and are never added together.
Small business
QuickBooks Online24%Contested▼−18Since October 2026: 42% → 24%, −18 points. Past the 10-point floor: movement.This pageMid-market
Zoho Books23%Contested↗new leaderNew leader since October 2026: Zoho Books (23%) replaces Sage Intacct (22% then, 12% now), 11 points clear, past the 10-point floor.Standing →Enterprise
Vic.ai15%Contested=heldSince October 2026: 15% → 15%, ±0 points. Inside the 10-point floor: within noise.Standing →
QuickBooks Online24%Contested▼−18Since October 2026: 42% → 24%, −18 points. Past the 10-point floor: movement.This pageMid-marketZoho Books23%Contested↗new leaderNew leader since October 2026: Zoho Books (23%) replaces Sage Intacct (22% then, 12% now), 11 points clear, past the 10-point floor.Standing →EnterpriseVic.ai15%Contested=heldSince October 2026: 15% → 15%, ±0 points. Inside the 10-point floor: within noise.Standing →The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for a small B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince October 2026
01QuickBooks Online24%8%50accepted challenger▼−18Since October 2026: 42% → 24%, −18 points. Past the 10-point floor: movement.42% → 24%
QuickBooks Online24%8%50accepted challenger▼−18Since October 2026: 42% → 24%, −18 points. Past the 10-point floor: movement.42% → 24%02
Xero12%0%53accepted challenger=heldSince October 2026: 12% → 12%, ±0 points. Inside the 10-point floor: within noise.12% → 12%
Xero12%0%53accepted challenger=heldSince October 2026: 12% → 12%, ±0 points. Inside the 10-point floor: within noise.12% → 12%03Zoho Books12%0%23accepted challenger▲+6Since October 2026: 6% → 12%, +6 points. Inside the 10-point floor: within noise.6% → 12%
Zoho Books12%0%23accepted challenger▲+6Since October 2026: 6% → 12%, +6 points. Inside the 10-point floor: within noise.6% → 12%04
Digits12%8%24accepted challenger▲+10Since October 2026: 2% → 12%, +10 points. Inside the 10-point floor: within noise.2% → 12%
Digits12%8%24accepted challenger▲+10Since October 2026: 2% → 12%, +10 points. Inside the 10-point floor: within noise.2% → 12%05
BILL8%0%16accepted challenger▲+6Since October 2026: 2% → 8%, +6 points. Inside the 10-point floor: within noise.2% → 8%
BILL8%0%16accepted challenger▲+6Since October 2026: 2% → 8%, +6 points. Inside the 10-point floor: within noise.2% → 8%06
Wave8%19%16accepted challenger=heldSince October 2026: 8% → 8%, ±0 points. Inside the 10-point floor: within noise.8% → 8%
Wave8%19%16accepted challenger=heldSince October 2026: 8% → 8%, ±0 points. Inside the 10-point floor: within noise.8% → 8%07
Puzzle2%0%12accepted challenger▼−2Since October 2026: 4% → 2%, −2 points. Inside the 10-point floor: within noise.4% → 2%
Puzzle2%0%12accepted challenger▼−2Since October 2026: 4% → 2%, −2 points. Inside the 10-point floor: within noise.4% → 2%08Vic.ai2%15%13accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%
Vic.ai2%15%13accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%09
Booke AI2%0%10accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%
Booke AI2%0%10accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 10-point floor: within noise.0% → 2%Show the seven products at 0%, ordered by negative rate
16
Botkeeper0%21%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
Botkeeper0%21%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%11
Zeni0%15%20accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 10-point floor: within noise.2% → 0%
Zeni0%15%20accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 10-point floor: within noise.2% → 0%15
Pilot0%10%10accepted challenger▼−4Since October 2026: 4% → 0%, −4 points. Inside the 10-point floor: within noise.4% → 0%
Pilot0%10%10accepted challenger▼−4Since October 2026: 4% → 0%, −4 points. Inside the 10-point floor: within noise.4% → 0%14
Ramp Accounting Agent0%9%11accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
Ramp Accounting Agent0%9%11accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%10
Docyt0%0%16accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
Docyt0%0%16accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%12
FreshBooks0%0%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%
FreshBooks0%0%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise.0% → 0%13
Dext0%0%11accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 10-point floor: within noise.2% → 0%
Dext0%0%11accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 10-point floor: within noise.2% → 0%The floor is 10 points of share, measured: how far the models move a leader on their own when the same questions are asked twice with nothing changed. A larger change is movement; a smaller one can't be told apart from repeat variation, and both are shown. Each index measures its own floor from its own repeat, over its own categories, so the floor differs from one index to the next. Both editions asked the same fourteen models. How the floor is measured
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
For buyers
Head to headHead-to-head pages are published for mid-market buyers, so these open on mid-market figures, not small business.
All twenty-eight head-to-head pages: the top eight products, each against each
Zoho Books vs NumericZoho Books vs Vic.aiZoho Books vs XeroZoho Books vs Ramp Accounting AgentRillet vs Sage IntacctRillet vs QuickBooks OnlineRillet vs NumericRillet vs Vic.aiRillet vs XeroRillet vs Ramp Accounting AgentSage Intacct vs QuickBooks OnlineSage Intacct vs NumericSage Intacct vs Vic.aiSage Intacct vs XeroSage Intacct vs Ramp Accounting AgentQuickBooks Online vs NumericQuickBooks Online vs Vic.aiQuickBooks Online vs XeroQuickBooks Online vs Ramp Accounting AgentNumeric vs Vic.aiNumeric vs XeroNumeric vs Ramp Accounting AgentVic.ai vs XeroVic.ai vs Ramp Accounting AgentXero vs Ramp Accounting Agent
Recommended versus criticized
Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.
Criticized challengerCriticized default
Negative label rate →
01020304050607080910111213141516Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01QuickBooks Online24%
QuickBooks Online24%02Xero12%
Xero12%03Zoho Books12%
Zoho Books12%04Digits12%
Digits12%05BILL8%
BILL8%06Wave8%
Wave8%07Puzzle2%
Puzzle2%08Vic.ai2%
Vic.ai2%09Booke AI2%
Booke AI2%10Docyt0%
Docyt0%11Zeni0%
Zeni0%12FreshBooks0%
FreshBooks0%13Dext0%
Dext0%14Ramp Accounting Agent0%
Ramp Accounting Agent0%15Pilot0%
Pilot0%16Botkeeper0%
Botkeeper0%What they warned about
Three of fourteen models held their first choice under the paraphrase. 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, GLM 4.7 FlashX, MiniMax M2.5 and GPT-6 Luna changed. A high negative share on a product with few labels is a warning. A low share on a product with many labels is salience, not sentiment.
ChatGPT
88%
7 of 8 labels negative · 7 of 14 models · 6 hard negative
“tools like ChatGPT or Claude can explain tax rules or summarize financial data, they are not designed to maintain accurate books” Mistral Small, negative prompt
Claude71%
5 of 7 labels negative · 5 of 14 models · 4 hard negative
“ChatGPT, Claude, and similar large language models (LLMs) are frequently used by small business owners for financial advice... Why to Avoid: Using these tools for sensitive financial data constitutes a data breach risk.” GLM 4.7 FlashX, negative prompt
Gemini
100%
4 of 4 labels negative · 4 of 14 models · 3 hard negative
“when staff use tools like ChatGPT, Gemini, or other AI apps without firm approval—is a fast-growing issue” Claude Haiku 4.5, negative prompt
QuickBooks Online8%
4 of 50 labels negative · 4 of 14 models
“general tools like QuickBooks AI (which is solid but less "agent-like")” Grok 4.20, paraphrase prompt
What they cite
Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted.
Sites the answers cite
78 of 84 answers in this category came back with a source list, from 14 of 14 models: citations where the model returns them, or the search results it consulted. 837 links across 267 sites, every framing counted. Ranked by the number of answers carrying the site or page. 6 of the 252 answers across every segment cited this index's own page for the category; the method page measures whether that reading tilts an answer.
vendor site · Xero35 answers · 64 citations · 13 models
26 answers · 35 citations · 11 models
22 answers · 34 citations · 9 models
vendor site · HelloBooks.ai18 answers · 33 citations · 8 models
16 answers · 17 citations · 10 models
vendor site · Zeni14 answers · 23 citations · 8 models
12 answers · 14 citations · 8 models
vendor site · CellCog12 answers · 12 citations · 9 models
12 answers · 12 citations · 8 models
12 answers · 12 citations · 6 models
11 answers · 12 citations · 8 models
11 answers · 11 citations · 9 models
Pages the answers cite
The ten pages named in the most answers, by full address. A page here is one the models returned with a recommendation, not one the index endorses.
18 answers · 11 models
16 answers · 10 models
15 answers · 9 models
12 answers · 9 models
12 answers · 8 models
12 answers · 6 models
12 answers · 8 models
10 answers · 4 models
10 answers · 6 models
9 answers · 4 models
Search against answers
Each company's standing in the answers beside its site's footprint in Google search, one row a site: the products the models named on it with their shares, and the share they add up to; monthly searches on Google, and DataForSEO's estimate of AI search demand (modeled from search signals, directional, not a count of queries to any assistant), for the most-searched of the company's and its products' names (the name is in each row's hover text); estimated monthly organic visits to the site; and its best position in Google's top ten for “ai accounting tools”, “ai bookkeeping tool”, “best ai bookkeeping tool”. US estimates from DataForSEO and Google's Ads Transparency Center. A small company's site, or a mid-sized company's site for its flagship, is marked company; a product on a large parent's site (Google, Microsoft) has no site figures. A column with no figures for this category is left out, and an empty cell means none were seen, not none exist. Two measurements side by side: neither is read as the cause of the other.
| Company and products | Share | Own site cited | Name searches, Google | AI search demand, est. | Organic visits | Paid search a month, est. | Google ads, last 30 days | Best Google position |
|---|---|---|---|---|---|---|---|---|
| QuickBooks quickbooks.ninja QuickBooks Online 24% | 24% | 692 | 1,000,000 | 54,681 | 253 company | |||
| Xero xero.com Xero 12%, Xero with JAX AI 2% | 14% | 729 | 90,500 | 4,610 | 1,200,289 | $500 | 119 | |
| Zoho zoho.com Zoho Books 12% | 12% | 367 | 27,100 | 268 | 1,216,894 company | $51,031 | 119 | |
| Digits digits.com | 12% | 70 | 40,500 | 465,781 | 49,788 | 0 | ||
| BILL bill.com | 8% | 374 | 2,740,000 | 1,063,001 | 1,783,039 | $199,231 | 119 | |
| Wave waveapps.com | 8% | 363 | 368,000 | 253,218 | 708,862 | 39 | ||
| Puzzle puzzle.io | 2% | 43 | 368,000 | 269,497 | 6,484 | $231 | 30 | |
| Vic.ai vic.ai | 2% | 82 | 720 | 0 | 1,251 | 1 | ||
| Booke booke.ai Booke AI 2% | 2% | 29 | 320 | 3,307 | 759 company | 1 | ||
| HelloBooks.ai hellobooks.ai | 2% | 7 |
Google's top ten for the three searches hold 22 sites; 2 of them are among the sites the models cited here (fitsmallbusiness.com, intuit.com). The first result for “ai accounting tools” is finlens.app.
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.ShowHide
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.
ShowHideModelDirect“What is the best AI bookkeeping tool for a small B2B company?”Paraphrase“Which AI agent for accounting tasks would you recommend to a small business that sells to other businesses?”Comparative“What are the top AI accounting tools for a small team and how do they differ?”Budget-constrained“What is the best AI bookkeeping tool for a small company with a tight budget?”Scale-constrained“We are a 30 person company evaluating an AI bookkeeping tool. What should we look at?”Negative“Which AI accounting tools should a small business avoid or be cautious about?”
Claude Haiku 4.5QuickBooks OnlineBILL, InvoicedChangedQuickBooks Online, XeroWaveno first choiceagainst: ChatGPT, Gemini
Five alternatives
Botkeeper, Tofu, Vic.ai, Xero, Zoho BooksThree alternatives
Lunos AI, Mesha, QuickBooks with Intuit AIThree alternatives
BILL, Wave, Zoho BooksTwo alternatives
Bookeeping.ai, QuickBooks OnlineGPT-5.4 miniQuickBooks Online with Intuit IntelligenceQuickBooks OnlineChangedQuickBooks Online with Intuit Intelligence, XeroXeroagainst: Botkeeperno first choicenothing named
Three alternatives
Dext, Xero, ZeniTwo alternatives
BILL, Sage IntacctSix alternatives
BILL, Botkeeper, Dext, FreshBooks, Vic.ai, Zoho BooksOne alternative
QuickBooks OnlineGemini 3.5 FlashQuickBooks Online, XeroBILLChangedQuickBooks Online, XeroPuzzleagainst: Bench, Zenino first choiceagainst: Oracle NetSuiteagainst: ChatGPT, Claude, Gemini, ScaleFactor
Six alternatives
BILL, Brex, Docyt, Puzzle, Ramp Accounting Agent, ZeniFour alternatives
QuickBooks Online, Upflow, Xero, ZeniFive alternatives
Dext, Docyt, Ramp Accounting Agent, Truewind, ZeniFive alternatives
Booke AI, QuickBooks Online, Wave, Xero, Zoho BooksPerplexity SonarQuickBooks Online with Intuit's AI featuresQuickBooks Online with its built-in Accounting AgentChangedagainst: PilotQuickBooks Online, XeroZoho Booksagainst: Digitsno first choiceagainst: ChatGPT, Claude, Gemini
Four alternatives
BILL, Digits, Pilot, XeroTwo alternatives
BILL, XeroFive alternatives
Digits, Docyt, FreshBooks, Kick, Zoho BooksTwo alternatives
QuickBooks Online, XeroGrok 4.20QuickBooks Online, XeroBooke AIChangedagainst: Numeric, QuickBooks Online, Ramp Accounting Agent, Vic.aiQuickBooks Online, Xeroagainst: ZeniWaveno first choiceagainst: ChatGPT, Grok
Two alternatives
FreshBooks, Zoho BooksThree alternatives
Botkeeper, Docyt, ZeniFour alternatives
BILL, Botkeeper, Digits, DocytFour alternatives
FreshBooks, QuickBooks Online, Ramp Accounting Agent, XeroThree alternatives
QuickBooks Online, Sage Intacct, XeroMistral SmallDigitsBILL, Vic.aiChangedFreshBooks, QuickBooks Online, XeroXerono first choiceagainst: ChatGPT, Claude
Three alternatives
Bookeeping.ai, OCTA Flow, ccMonetThree alternatives
Digits, Docyt, MeshaFour alternatives
Docyt, Ramp Accounting Agent, Vic.ai, Zoho BooksTwo alternatives
Puzzle, QuickBooks OnlineDeepSeek V4 FlashDigitsBILLChangedQuickBooks Online, Xeroagainst: ZeniZoho Booksno first choiceagainst: Benchagainst: Digits, QuickBooks Online
Three alternatives
Booke AI, QuickBooks Online, XeroTwo alternatives
QuickBooks Online, SpinnableFour alternatives
Dext, Digits, Docyt, Vic.aiFive alternatives
Digits, FreshBooks, Puzzle, Wave, XeroLlama 4 MaverickDigitsno first choiceChangedno first choiceDigitsno first choicenothing named
Two alternatives
Zeni, Zoho BooksThree alternatives
Bookeeping.ai, Xero, Zoho BooksQwen 3.7 FlashDigitsDigitsHeldQuickBooks Online, XeroQuickBooks OnlinePentanaagainst: Botkeeper
Five alternatives
Bench, Booke AI, Dext, Pilot, TofuFour alternatives
Invoiced, LedgerUp, Pilot, ZeniFour alternatives
BILL, Botkeeper, Vic.ai, Zoho BooksFour alternatives
Dext, JAX in Xero, Puzzle, XeroFive alternatives
BlackLine, Botkeeper, Harvest, Helloscale, Ramp/BrexKimi K2QuickBooks OnlineQuickBooks OnlineHeldXeroWave, Zoho Booksno first choiceagainst: ChatGPT, Claude, Gemini
Three alternatives
CellCog, Docyt, XeroTwo alternatives
Docyt, LedgerUpEight alternatives
BILL, Digits, FreshBooks, Melio, Puzzle, QuickBooks Online, Ramp Accounting Agent, ZeniTwo alternatives
QuickBooks Online, XeroGLM 4.7 FlashXQuickBooks Online, XeroLedgerUpChangedQuickBooks Online, Xeroagainst: WaveHelloBooks.ai, Zoho Booksno first choiceagainst: Botkeeper, ChatGPT, Claude
Three alternatives
HelloBooks.ai, Pilot, ZeniThree alternatives
HelloBooks.ai, Vic.ai, XeroSeven alternatives
BILL, Botkeeper, Docyt, Sage Intacct, Vic.ai, Zeni, Zoho BooksTwo alternatives
QuickBooks Online, WaveMiniMax M2.5CellCog, QuickBooks OnlineXero with JAX AIChangedQuickBooks Onlineagainst: WaveWaveagainst: QuickBooks Onlineno first choiceagainst: Wave
Two alternatives
Booke AI, XeroTwo alternatives
FreshBooks, QuickBooks OnlineThree alternatives
Truewind, Vic.ai, XeroTwo alternatives
Xero, Zoho BooksGPT-6 LunaQuickBooks OnlineQuickBooks Online with Intuit's built-in AIChangedQuickBooks OnlineZoho Booksno first choicenothing named
Two alternatives
Puzzle, XeroOne alternative
DigitsFour alternatives
Digits, Puzzle, Xero, Zoho BooksOne alternative
WaveMuse Glimmer 30BQuickBooks OnlineQuickBooks OnlineHeldQuickBooks Online, XeroXero, Zoho Booksagainst: QuickBooks Onlineno first choiceagainst: Stampli, Truewind, Vic.ai
Four alternatives
Digits, Pilot, Xero, ZeniTwo alternatives
BILL, XeroSix alternatives
Botkeeper, Dext, formerly Receipt Bank, Digits, Pilot, Zeni, Zoho BooksTwo alternatives
HelloBooks.ai, WaveBold is the first choiceAlternatives are counted; the count opens them.What the answer argued against
The record
One row per call: the version string exactly as returned, whether the model searched, sources cited, and latency.
Eighty-four rows: every prompt, every model, every answer.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|---|---|---|---|---|---|
| Direct recommendation | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:54 | yes | 10 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:02 | yes | 5 | 4 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 11:05 | yes | 10 | 17 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 09:02 | yes | 10 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:22 | yes | 10 | 31 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:34 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:20 | yes | 24 | 20 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:18 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:33 | yes | 5 | 20 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:50 | yes | 5 | 12 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:49 | yes | 10 | 25 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 08:49 | yes | 5 | 17 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:34 | yes | 3 | 13 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:24 | yes | 15 | 19 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:42 | yes | 18 | 8 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 09:14 | yes | 3 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:40 | yes | 10 | 18 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 12:39 | yes | 10 | 4 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:11 | yes | 5 | 29 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:23 | yes | 5 | 4 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 12:42 | yes | 24 | 23 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:47 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 09:43 | yes | 10 | 16 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 12:25 | yes | 15 | 38 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:48 | yes | 24 | 70 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:48 | yes | 5 | 62 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:14 | yes | 3 | 13 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:31 | yes | 12 | 18 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 12:56 | yes | 10 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:34 | yes | 5 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 08:53 | yes | 10 | 20 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 10:34 | yes | 10 | 5 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:26 | yes | 5 | 34 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:08 | yes | 5 | 7 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 12:54 | yes | 23 | 44 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:50 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:56 | yes | 5 | 35 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 12:53 | yes | 15 | 31 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:44 | yes | 23 | 39 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:25 | yes | 20 | 64 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 12:54 | yes | 5 | 25 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:54 | yes | 13 | 28 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:08 | yes | 9 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:18 | yes | 4 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:37 | yes | 9 | 21 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 11:04 | yes | 10 | 3 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:25 | yes | 5 | 25 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:03 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:01 | yes | 23 | 31 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:58 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:43 | yes | 5 | 12 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:37 | yes | 9 | 25 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:45 | yes | 10 | 20 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 10:22 | yes | 5 | 33 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:40 | yes | 3 | 17 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:02 | yes | 12 | 23 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 10:39 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 08:49 | no | 0 | 6 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:20 | no | 0 | 14 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 10:16 | yes | 10 | 7 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:06 | yes | 14 | 37 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:05 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:07 | yes | 16 | 24 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 12:35 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:01 | no | 0 | 30 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:48 | yes | 20 | 23 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:03 | yes | 15 | 27 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:42 | yes | 5 | 28 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:37 | yes | 2 | 12 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:45 | yes | 15 | 18 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:09 | yes | 19 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:24 | yes | 5 | 5 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:16 | yes | 15 | 19 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 09:00 | yes | 10 | 5 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 13:12 | yes | 10 | 30 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:51 | yes | 5 | 7 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:09 | yes | 25 | 29 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 10:21 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:21 | yes | 25 | 30 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:18 | yes | 23 | 66 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:32 | yes | 25 | 90 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 08:41 | no | 0 | 26 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 12:36 | yes | 4 | 13 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:00 | yes | 25 | 35 s |
Normalization in this category
Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.
ShowHide
Category-scoped readings
Dext Prepare read as Dext
HelloBooks read as HelloBooks.ai
Netsuite read as Oracle NetSuite
QuickBooks read as QuickBooks Online
QuickBooks Online Simple Start read as QuickBooks Online
Ramp read as Ramp Accounting Agent
Sage read as Sage Intacct
Wave Accounting read as Wave
Unresolved, counted raw
Counto
Elephas
Energent.ai / Zeni
Helloscale
JAX in Xero
OpenClaw
Pentana
QB Online
QuickBooks Online with Intuit's AI features
QuickBooks Online with Intuit's built-in AI
QuickBooks Online with its built-in Accounting Agent
QuickBooks with Intuit AI
QuickBooks' SmartSearch
ScaleFactor
SparkReceipt
Spinnable
Xero\u2019s Hubdoc
Discontinued, still offered
No shut-down product was recommended here.