AI accounting assistants
Asked as “AI bookkeeping tool”, and as “AI agent for accounting tasks”, on behalf of a mid-market B2B company. 44 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Standing · first-choice share
25%
Contested · Zoho Books 18%
25Sage Intacct18Zoho Books09Ramp Accounting Agent48others
25% of first choices, contested.
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.
The standing
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. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
Show the five products at 0%, ordered by negative rate
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.
Claude is made by Anthropic, whose model Claude Haiku 4.5 is in the set. On the four share prompts that model made it the first choice zero times of 4; the other eleven models zero times of 44. ChatGPT is made by OpenAI, whose model GPT-5.4 mini is in the set. On the four share prompts that model made it the first choice zero times of 4; the other eleven models zero times of 44. Lab treatment is defined on the method page; the row is marked, not excluded.
All twenty-eight head-to-head pages: the top eight products, each against each
Sage Intacct vs XeroSage Intacct vs NumericSage Intacct vs FreshBooksSage Intacct vs DocytZoho Books vs Ramp Accounting AgentZoho Books vs Vic.aiZoho Books vs XeroZoho Books vs NumericZoho Books vs FreshBooksZoho Books vs DocytRamp Accounting Agent vs Vic.aiRamp Accounting Agent vs XeroRamp Accounting Agent vs NumericRamp Accounting Agent vs FreshBooksRamp Accounting Agent vs DocytVic.ai vs XeroVic.ai vs NumericVic.ai vs FreshBooksVic.ai vs DocytXero vs NumericXero vs FreshBooksXero vs DocytNumeric vs FreshBooksNumeric vs DocytFreshBooks vs Docyt
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 →
01
02
03
04
05
06
07
08
09
10
11
12
13C14
Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Sage Intacct25%
Sage Intacct25%02Zoho Books18%
Zoho Books18%03Ramp Accounting Agent9%
Ramp Accounting Agent9%04Vic.ai7%
Vic.ai7%05Xero7%
Xero7%06Numeric7%
Numeric7%07FreshBooks2%
FreshBooks2%08Docyt2%
Docyt2%09BILL2%
BILL2%10QuickBooks Online0%
QuickBooks Online0%11FloQast0%
FloQast0%12Zeni0%
Zeni0%13Claude0%
Claude0%14ChatGPT0%
What they warned about
One of twelve models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Perplexity Sonar, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX and MiniMax M2.5 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
92%
11 of 12 labels negative · 8 of 12 models · 7 hard negative
“You should never use public-facing consumer AI models (such as standard free tiers of ChatGPT, Bard, or generic LLM interfaces) to process your actual client ledgers” Qwen 3.7 Flash, negative prompt
Claude100%
10 of 10 labels negative · 8 of 12 models · 5 hard negative
“public, non-enterprise AI chatbots should never be used to run your books or research complex tax regulations” Gemini 3.5 Flash, negative prompt
Gemini
100%
5 of 5 labels negative · 5 of 12 models · 4 hard negative
“never use public-facing consumer AI models (such as standard free tiers of ChatGPT, Bard, or generic LLM interfaces) to process your actual client ledgers” Qwen 3.7 Flash, negative prompt
QuickBooks Online22%
8 of 36 labels negative · 5 of 12 models
“Unlike small businesses that can run their entire ledger on simple, automated tools like QuickBooks Online, Zeni, or Inkle” Gemini 3.5 Flash, direct prompt
What they cite
Twelve of the twelve models returned a source list in this edition: four return the pages they cited and eight the search results they consulted.
Sites the answers cite
66 of 72 answers in this category came back with a source list, from 12 of 12 models: citations where the model returns them, or the search results it consulted. 858 links across 279 sites, every framing counted. Ranked by the number of answers carrying the site or page.
30 answers · 30 citations · 10 models
vendor site · DualEntry25 answers · 29 citations · 10 models
22 answers · 23 citations · 10 models
vendor site · Numeric21 answers · 23 citations · 11 models
17 answers · 24 citations · 6 models
17 answers · 17 citations · 9 models
17 answers · 17 citations · 9 models
14 answers · 19 citations · 7 models
14 answers · 16 citations · 6 models
12 answers · 12 citations · 10 models
12 answers · 12 citations · 7 models
vendor site · Fast.io11 answers · 11 citations · 10 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.
30 answers · 10 models
24 answers · 10 models
19 answers · 10 models
17 answers · 9 models
15 answers · 9 models
15 answers · 10 models
14 answers · 6 models
12 answers · 10 models
11 answers · 5 models
11 answers · 10 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 |
|---|---|---|---|---|---|---|---|
| Sage sage.com Sage Intacct 25% | 25% | 500 | 246,000 | 90,599 | 1,737,127 company | $114,671 | 78 |
| Zoho zoho.com Zoho Books 18% | 18% | 367 | 27,100 | 268 | 1,216,894 company | $51,031 | 119 |
| Ramp Accounting Agent ramp.com | 9% | 36 | 70 | 0 | 770,056 | $13,511 | 120 |
| Vic.ai vic.ai | 7% | 82 | 720 | 0 | 1,251 | 1 | |
| Xero xero.com | 7% | 729 | 90,500 | 4,610 | 1,200,289 | $500 | 119 |
| Numeric numeric.io | 7% | 201 | 12,100 | 38,006 | 94,254 | $426 | 9 |
| Wave waveapps.com | 7% | 363 | 368,000 | 253,218 | 708,862 | 39 | |
| Kick | 5% | ||||||
| Ledge ledge.co | 5% | 3 | 18,100 | 7,714 | 1,897 | 23 | |
| FreshBooks freshbooks.com | 2% | 304 | 40,500 | 389 | 305,801 | $221 | 113 |
Google's top ten for the three searches hold 22 sites; 2 of them are among the sites the models cited here (dualentry.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 mid-market B2B company?”Paraphrase“Which AI agent for accounting tasks would you recommend to a mid-sized B2B company?”Comparative“What are the top AI accounting tools and how do they differ?”Budget-constrained“What is the best AI bookkeeping tool for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating an AI bookkeeping tool. What should we look at?”Negative“Which AI accounting tools should I avoid or be cautious about?”
Claude Haiku 4.5Vic.aiRamp Accounting AgentChangedDualEntryZoho Booksno first choicenothing named
Four alternatives
Booke AI, DualEntry, Integra Balance AI, Sage IntacctTwo alternatives
Docyt, Vic.aiEight alternatives
Anrok, Fathom, QuickBooks Online, Trullion, Vic.ai, Xero, Zeni, Zone & CoThree alternatives
Bookeeping.ai, Kick, LayerNextGPT-5.4 miniSage Intacctagainst: QuickBooks Online, XeroBILLChangedno first choiceXeroagainst: Booke AIno first choicenothing named
Four alternatives
FloQast, Hyperbots A/P Suite, Microsoft Dynamics 365 Business Central, Oracle NetSuiteThree alternatives
Intuit Enterprise Suite, Payhawk, Sage IntacctOne alternative
QuickBooks OnlineGemini 3.5 FlashLedge, Numericagainst: Inkle, QuickBooks Online, ZeniNumericChangedQuickBooks Online, XeroKickagainst: Pilot, Wave, Zenino first choiceagainst: ChatGPT, Claude, Gemini
Three alternatives
Ramp Accounting Agent, Tabs, Vic.aiFour alternatives
Ledge, Oracle NetSuite, Sage Intacct, Vic.aiNine alternatives
BILL, Booke AI, Brex, Numeric, Ramp Accounting Agent, Truewind, Trullion, Vic.ai, ZeniFour alternatives
Bookeeping.ai, HelloBooks.ai, Xero, Zoho BooksPerplexity SonarSage IntacctRamp Accounting AgentChangedno first choiceWave, Xeroagainst: QuickBooks Onlineno first choiceagainst: ChatGPT, Claude, Gemini
Three alternatives
DualEntry, Numeric, Vic.aiFour alternatives
FloQast, Numeric, QuickBooks Online, Vic.aiTwelve alternatives
Anrok, BILL, Dext, FloQast, MindBridge, Numeric, QuickBooks Online, Ramp Accounting Agent, Tabs, Trullion, Vic.ai, XeroOne alternative
Zoho BooksGrok 4.20Sage Intacctagainst: QuickBooks OnlineSage IntacctHeldagainst: QuickBooks Online, XeroQuickBooks Online, XeroZoho Booksagainst: QuickBooks Onlineno first choiceagainst: Air AI, Booke AI, ChatGPT, Claude, Digits, Grok, QuickBooks Online, Sage Copilot, Stampli, Vic.ai
Four alternatives
Docyt, Oracle NetSuite, QuickBooks Online, XeroTwo alternatives
FloQast, Vic.aiFive alternatives
Digits, Docyt, Ramp Accounting Agent, Vic.ai, ZeniTwo alternatives
Wave, XeroFour alternatives
Botkeeper, Netgain, QuickBooks Online, XeroMistral SmallSage IntacctVic.aiChangedno first choiceagainst: ChatGPT, ClaudeZoho Booksno first choiceagainst: ChatGPT, Claude, Gemini
Two alternatives
Truewind, Vic.aiTwo alternatives
FloQast, Sage CopilotThree alternatives
Bookeeping.ai, FreshBooks, QuickBooks OnlineDeepSeek V4 FlashRho, Sage IntacctRamp Accounting AgentChangedagainst: BILLQuickBooks Online, Xeroagainst: ChatGPT, Claude, Microsoft CopilotZoho Booksagainst: Bench, Truewind, Zenino first choiceagainst: Basis, Bench, Booke AI, Digits, Pilot, Puzzle, Truewind, Zeniagainst: Bench, Botkeeper, ChatGPT, DeepSeek, Meta AI, Ramp Accounting Agent, Sage Copilot
Three alternatives
Oracle NetSuite, Vic.ai, ZeniFive alternatives
FloQast, Numeric, Oracle NetSuite, Sage Copilot, Vic.aiEight alternatives
BILL, DOKKA, Dext, Docyt, FloQast, Karbon, Numeric, Vic.aiFive alternatives
Bookeeping.ai, Puzzle, QuickBooks Online, Wave, XeroThree alternatives
Numeric, Trullion, Vic.aiLlama 4 MaverickSage Intacctno first choiceChangedno first choiceZoho Booksno first choicenothing named
Two alternatives
Truewind, Vic.aiThree alternatives
Bookeeping.ai, FreshBooks, QuickBooks OnlineQwen 3.7 FlashDualEntrySage IntacctChangedQuickBooks Onlineagainst: ChatGPT, Claude, Vic.aiWave, Zoho Booksno first choiceagainst: ChatGPT, Claude, Gemini
Two alternatives
Sage Intacct, Vic.aiThree alternatives
FloQast, Ramp Accounting Agent, Vic.aiFive alternatives
Botkeeper, Dext, FloQast, Numeric, XeroOne alternative
XeroKimi K2Sage Intacctagainst: TruewindNumericChangedQuickBooks OnlineWave, Zoho Booksagainst: Benchno first choiceagainst: ChatGPT, Claude
Three alternatives
DualEntry, Numeric, Vic.aiFour alternatives
FloQast, Pilot, Sage Intacct, Vic.aiFive alternatives
Dext, Fathom, FloQast, FreshBooks, XeroTwo alternatives
Bookeeping.ai, QuickBooks OnlineGLM 4.7 FlashXSage Intacctagainst: QuickBooks OnlineDocyt, Vic.aiChangedQuickBooks OnlineKick, Zoho Booksno first choiceagainst: ChatGPT, Claude, DeepSeek, Gemini, Grok, Meta AI
Two alternatives
Docyt, ZeniTwo alternatives
BILL, Ramp Accounting AgentNine alternatives
Dext, Fathom, FloQast, Numeric, Ramp Accounting Agent, Tabs, Trullion, Vic.ai, XeroFour alternatives
FreshBooks, Puzzle, QuickBooks Online, XeroMiniMax M2.5Sage IntacctLedge, Ramp Accounting AgentChangedQuickBooks OnlineFreshBooks, Xerono first choiceagainst: Botkeeper
Three alternatives
DualEntry, Truewind, Vic.aiTwo alternatives
Docyt, Vic.aiTen alternatives
BILL, Dext, Fathom, FreshBooks, Microsoft Copilot for Finance, Numeric, Ramp Accounting Agent, Sage Copilot, Trullion, XeroTwo alternatives
Double, Zoho BooksBold 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.
Seventy-two 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 | 2026-09-17 19:10 | yes | 9 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:35 | yes | 2 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 20:16 | yes | 16 | 22 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-09-17 20:14 | yes | 20 | 7 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 19:40 | yes | 35 | 17 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:50 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 19:53 | yes | 27 | 35 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:37 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:59 | yes | 10 | 41 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 17:58 | yes | 10 | 29 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 18:12 | yes | 24 | 78 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:01 | yes | 5 | 13 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 20:52 | yes | 17 | 9 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:44 | yes | 2 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 18:50 | yes | 13 | 19 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-09-17 19:59 | yes | 20 | 4 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 18:06 | yes | 31 | 15 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:07 | yes | 5 | 4 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 19:26 | yes | 19 | 21 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:53 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:03 | yes | 5 | 26 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 19:30 | yes | 9 | 20 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 20:00 | yes | 12 | 86 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 20:37 | yes | 5 | 13 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:15 | yes | 9 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 21:07 | yes | 4 | 10 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 19:16 | yes | 11 | 23 s |
| Comparative | Perplexity Sonar | sonar | 2026-09-17 20:42 | yes | 20 | 14 s |
| Comparative | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 20:30 | yes | 25 | 14 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 18:49 | yes | 5 | 6 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 19:56 | yes | 15 | 30 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:38 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 20:50 | yes | 5 | 13 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 20:19 | yes | 10 | 20 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:03 | yes | 8 | 32 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 20:00 | yes | 7 | 22 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 18:31 | yes | 9 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:51 | yes | 3 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 21:52 | yes | 17 | 21 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-09-17 18:24 | yes | 20 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 20:06 | yes | 33 | 15 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:34 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 20:23 | yes | 9 | 11 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:14 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:41 | yes | 5 | 20 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:02 | yes | 9 | 33 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:51 | yes | 14 | 18 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:10 | yes | 5 | 13 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:04 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:18 | no | 0 | 10 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 18:46 | no | 0 | 14 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-09-17 19:17 | yes | 20 | 10 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 19:45 | yes | 18 | 12 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 18:47 | no | 0 | 11 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 18:21 | yes | 15 | 21 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:01 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:31 | no | 0 | 30 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:40 | yes | 10 | 19 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:55 | yes | 15 | 184 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:15 | no | 0 | 12 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:15 | yes | 19 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 18:33 | yes | 5 | 7 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 21:17 | yes | 21 | 64 s |
| Negative framing | Perplexity Sonar | sonar | 2026-09-17 19:03 | yes | 20 | 7 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-17 19:15 | yes | 32 | 17 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:27 | yes | 5 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 20:37 | yes | 30 | 23 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:24 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:40 | yes | 14 | 49 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:16 | yes | 15 | 25 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:27 | yes | 15 | 26 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 18:19 | yes | 25 | 43 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
BILL AP/AR read as BILL
Bench Accounting read as Bench
Booke read as Booke AI
Dext Prepare read as Dext
NetSuite read as Oracle NetSuite
NetSuite (Intelligent Close) read as Oracle NetSuite
NetSuite (Oracle) read as Oracle NetSuite
QuickBooks read as QuickBooks Online
QuickBooks (Simple Start) read as QuickBooks Online
QuickBooks Online Simple Start read as QuickBooks Online
QuickBooks Simple Start read as QuickBooks Online
Ramp read as Ramp Accounting Agent
Ramp Intelligence read as Ramp Accounting Agent
Ramp's AI spreadsheet tool read as Ramp Accounting Agent
Sage read as Sage Intacct
Unresolved, counted raw
Air AI
Blue J
Blue J/TaxGPT
DeskFerry
Elephas
Hyperbots A/P Suite
Integra Balance AI
Jupid
ZoneCapture
Discontinued, still offered
No shut-down product was recommended here.