AI accounting assistants
Asked as “AI bookkeeping tool”, and as “AI agent for accounting tasks”, on behalf of a mid-market B2B company. 46 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
22%
Contested · Rillet 11%
22Sage Intacct11Rillet11Zoho Books57others
22% of first choices, contested.
Since September 2026▼−2Since September 2026: 25% → 23%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.Sage Intacct held the lead, −2 points on 25%, inside the 10-point 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 Online42%Clear leader▲+4Since September 2026: 40% → 44%, +4 points. Inside the 10-point floor: within noise. Read over the models both editions asked.Standing →Mid-market
Sage Intacct22%Contested▼−2Since September 2026: 25% → 23%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.This pageEnterprise
Vic.ai15%Contested▲+5Since September 2026: 12% → 17%, +5 points. Inside the 10-point floor: within noise. Read over the models both editions asked.Standing →
QuickBooks Online42%Clear leader▲+4Since September 2026: 40% → 44%, +4 points. Inside the 10-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketSage Intacct22%Contested▼−2Since September 2026: 25% → 23%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.This pageEnterpriseVic.ai15%Contested▲+5Since September 2026: 12% → 17%, +5 points. Inside the 10-point floor: within noise. Read over the models both editions asked.Standing →The standing
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. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince September 2026
01Sage Intacct22%0%24accepted challenger▼−2Since September 2026: 25% → 23%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.25% → 23%
Sage Intacct22%0%24accepted challenger▼−2Since September 2026: 25% → 23%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.25% → 23%03
Zoho Books11%8%13accepted challenger▼−10Since September 2026: 18% → 8%, −10 points. Past the 10-point floor: movement. Read over the models both editions asked.18% → 8%
Zoho Books11%8%13accepted challenger▼−10Since September 2026: 18% → 8%, −10 points. Past the 10-point floor: movement. Read over the models both editions asked.18% → 8%04Vic.ai9%7%30accepted challenger▲+3Since September 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 10%
Vic.ai9%7%30accepted challenger▲+3Since September 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 10%05
Wave9%0%13accepted challenger▲+3Since September 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 10%
Wave9%0%13accepted challenger▲+3Since September 2026: 7% → 10%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 10%06
Numeric7%0%11accepted challenger▼−2Since September 2026: 7% → 5%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 5%
Numeric7%0%11accepted challenger▼−2Since September 2026: 7% → 5%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 5%07
Xero4%5%37accepted challenger▼−2Since September 2026: 7% → 5%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 5%
Xero4%5%37accepted challenger▼−2Since September 2026: 7% → 5%, −2 points. Inside the 10-point floor: within noise. Read over the models both editions asked.7% → 5%08
Digits4%20%10accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%
Digits4%20%10accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%09QuickBooks Online2%14%42accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%
QuickBooks Online2%14%42accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%10
Ramp Accounting Agent2%6%17accepted challenger▼−7Since September 2026: 9% → 3%, −7 points. Inside the 10-point floor: within noise. Read over the models both editions asked.9% → 3%
Ramp Accounting Agent2%6%17accepted challenger▼−7Since September 2026: 9% → 3%, −7 points. Inside the 10-point floor: within noise. Read over the models both editions asked.9% → 3%11
BILL2%0%15accepted challenger=heldSince September 2026: 2% → 3%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.2% → 3%
BILL2%0%15accepted challenger=heldSince September 2026: 2% → 3%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.2% → 3%12
Zeni2%10%10accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%
Zeni2%10%10accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%13
Docyt2%9%11accepted challenger=heldSince September 2026: 2% → 3%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.2% → 3%
Docyt2%9%11accepted challenger=heldSince September 2026: 2% → 3%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.2% → 3%14
Puzzle2%15%13accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%
Puzzle2%15%13accepted challenger▲+3Since September 2026: 0% → 3%, +3 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 3%Show the three products at 0%, ordered by negative rate
16
Booke AI0%17%12accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 0%
Booke AI0%17%12accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 0%17
Botkeeper0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 0%
Botkeeper0%10%10accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 0%15
Oracle NetSuite0%6%17accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 0%
Oracle NetSuite0%6%17accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 10-point floor: within noise. Read over the models both editions asked.0% → 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 is noise, and both are shown. Movement is read over the twelve models both editions asked; GPT-6 Luna, Muse Glimmer 30B joined this edition and are in the standing but not yet in the comparison. 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.
All twenty-eight head-to-head pages: the top eight products, each against each
Sage Intacct vs WaveSage Intacct vs NumericSage Intacct vs XeroSage Intacct vs DigitsRillet vs Zoho BooksRillet vs Vic.aiRillet vs WaveRillet vs NumericRillet vs XeroRillet vs DigitsZoho Books vs Vic.aiZoho Books vs WaveZoho Books vs NumericZoho Books vs XeroZoho Books vs DigitsVic.ai vs WaveVic.ai vs NumericVic.ai vs XeroVic.ai vs DigitsWave vs NumericWave vs XeroWave vs DigitsNumeric vs XeroNumeric vs DigitsXero vs Digits
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
02030405060708091011121314151617Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Sage Intacct22%
Sage Intacct22%02Rillet11%
Rillet11%03Zoho Books11%
Zoho Books11%04Vic.ai9%
Vic.ai9%05Wave9%
Wave9%06Numeric7%
Numeric7%07Xero4%
Xero4%08Digits4%
Digits4%09QuickBooks Online2%
QuickBooks Online2%10Ramp Accounting Agent2%
Ramp Accounting Agent2%11BILL2%
BILL2%12Zeni2%
Zeni2%13Docyt2%
Docyt2%14Puzzle2%
Puzzle2%15Oracle NetSuite0%
Oracle NetSuite0%16Booke AI0%
Booke AI0%17Botkeeper0%
Botkeeper0%What they warned about
Two 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 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Qwen 3.7 Flash, Kimi K2, 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
100%
8 of 8 labels negative · 8 of 14 models · 8 hard negative
“This includes tools like ChatGPT (free/Plus tiers), Claude, and Gemini when used with sensitive data. ChatGPT hallucinates specific numbers and regulatory details with confidence” Claude Haiku 4.5, negative prompt
Claude100%
6 of 6 labels negative · 6 of 14 models · 4 hard negative
“like public ChatGPT/Claude-style tools when used with client data, because they may lack robust security and may use inputs for training.” Perplexity Sonar, negative prompt
QuickBooks Online14%
6 of 42 labels negative · 4 of 14 models
“traditional tools (like QuickBooks, Xero, or even NetSuite with add-ons) are "layering" AI onto legacy batch-processing systems” Qwen 3.7 Flash, paraphrase prompt
Bench62%
5 of 8 labels negative · 3 of 14 models · 2 hard negative
“abruptly shut down, locking thousands of small businesses out of their financial data right before tax season... clients have continued to report reliability and support issues.” Gemini 3.5 Flash, negative prompt
What they cite
Citations exist only for the models that return a source list: fourteen of the fourteen in this edition, and all six flagship models on the expanded tier.
Sites the answers cite
77 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. 1100 links across 320 sites, every framing counted. Ranked by the number of answers carrying the site or page. 4 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 · Rillet33 answers · 57 citations · 11 models
33 answers · 33 citations · 12 models
31 answers · 36 citations · 12 models
29 answers · 39 citations · 9 models
vendor site · Ramp24 answers · 33 citations · 9 models
vendor site · Numeric23 answers · 34 citations · 10 models
vendor site · DualEntry18 answers · 18 citations · 10 models
18 answers · 18 citations · 8 models
vendor site · Xero15 answers · 19 citations · 10 models
12 answers · 22 citations · 7 models
12 answers · 15 citations · 8 models
vendor site · Digits11 answers · 17 citations · 8 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.
32 answers · 11 models
23 answers · 11 models
23 answers · 11 models
18 answers · 8 models
18 answers · 8 models
16 answers · 11 models
15 answers · 9 models
15 answers · 6 models
12 answers · 6 models
12 answers · 8 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 22% | 22% | 433 | 246,000 | 90,599 | 1,737,127 company | $114,671 | 78 |
| Rillet rillet.com | 11% | 39 | 8,100 | 168 | 4,712 | $4,776 | 56 |
| Zoho zoho.com Zoho Books 11% | 11% | 326 | 27,100 | 268 | 1,216,894 company | $51,031 | 119 |
| Vic.ai vic.ai | 9% | 93 | 720 | 0 | 1,251 | 1 | |
| Wave waveapps.com | 9% | 323 | 368,000 | 253,218 | 708,862 | 39 | |
| Numeric numeric.io | 7% | 218 | 12,100 | 38,006 | 94,254 | $426 | 9 |
| Xero xero.com | 4% | 737 | 90,500 | 4,610 | 1,200,289 | $500 | 119 |
| Digits digits.com | 4% | 37 | 40,500 | 465,781 | 49,788 | 0 | |
| QuickBooks quickbooks.ninja QuickBooks Online 2% | 2% | 621 | 1,000,000 | 54,681 | 253 company | ||
| Ramp Accounting Agent ramp.com | 2% | 45 | 70 | 0 | 770,056 | $13,511 | 120 |
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 4.5Sage IntacctStacksChangedQuickBooks Online, XeroDigitsno first choiceagainst: ChatGPT, Claude, Digits, Gemini, Puzzle
Three alternatives
Ramp Accounting Agent, Rillet, XeroFour alternatives
Docyt, FloQast, Ramp Accounting Agent, Vic.aiEleven alternatives
BILL, BlackLine, Brex, DualEntry, Netgain, Ramp Accounting Agent, Sage Intacct, Tabs, Trullion, Vic.ai, Zoho BooksThree alternatives
Bookeeping.ai, Finlens, Zoho BooksGPT-5.4 miniSage Intacctagainst: Hyperbots, OCTAIntuit Enterprise Suite's accounting agentChangedQuickBooks Onlineagainst: FreshBooks, Zoho BooksXeroagainst: Digits, Pilotno first choicenothing named
Two alternatives
FloQast, HighRadiusFour alternatives
Basis, Centime, Concourse, ZipTwo alternatives
Sage Intacct, XeroTwo alternatives
Papertools, QuickBooks OnlineGemini 3.5 FlashTruewindagainst: Bench, Puzzle, QuickBooks OnlineLedgeChangedDigitsPuzzleno first choiceagainst: Bench, ChatGPT, Claude, Gemini
Four alternatives
Numeric, Ramp Accounting Agent, Stampli, Vic.aiFive alternatives
Lunos AI, Numeric, Ramp Accounting Agent, Vic.ai, Zone & CoNine alternatives
Booke AI, Numeric, QuickBooks Online, Tabs, Truewind, Trullion, Vic.ai, Xero, ZeniFive alternatives
Booke AI, QuickBooks Online, Vuuv, Wave, XeroPerplexity SonarRillet, Sage IntacctNumericChangedNumericQuickBooks Onlineno first choiceagainst: ChatGPT, Claude
Two alternatives
Vic.ai, ZeniFour alternatives
BILL, FloQast, Ramp Accounting Agent, Vic.aiNine alternatives
BILL, Botkeeper, Docyt, Puzzle, QuickBooks Online, Rillet, Vic.ai, Xero, ZeniOne alternative
Zoho BooksGrok 4.1 FastSage IntacctFloQastChangedno first choiceWaveagainst: QuickBooks OnlineSage Intacctagainst: QuickBooks Onlineagainst: Booke AI, ChatGPT, Claude, Sage Copilot, Vic.ai
Two alternatives
Oracle NetSuite, XeroFour alternatives
BILL, Booke AI, Ramp Accounting Agent, Vic.aiOne alternative
Zoho BooksThree alternatives
Booke AI, Docyt, Vic.aiMistral SmallVic.aiBILLChangedno first choiceWaveno first choiceagainst: Booke AI, Vic.ai
Two alternatives
Oracle NetSuite, Sage IntacctTwo alternatives
Aura, Vic.aiOne alternative
QuickBooks OnlineDeepSeek V4 FlashRilletNumericChangedagainst: RilletQuickBooks OnlineZoho Booksagainst: Benchno first choiceagainst: Pilot, Truewindagainst: Bench, Docyt, Zeni
Three alternatives
Digits, Pilot, Sage IntacctThree alternatives
FloQast, Stampli, Vic.aiSeven alternatives
FreshBooks, Numeric, Ramp Accounting Agent, Sage Intacct, Trullion, Xero, Zoho BooksTwo alternatives
Wave, XeroThree alternatives
Oracle NetSuite, Rillet, Sage IntacctLlama 4 MaverickVic.aiVic.aiHeldno first choiceno first choiceno first choicenothing named
Three alternatives
BILL, Oracle NetSuite, Sage IntacctFour alternatives
BILL, Fazeshift's accounts receivable agents, Financial Cents, TrullionQwen 3.7 FlashSage Intacctagainst: QuickBooks Online, XeroRilletChangedagainst: Intuit AI, Oracle NetSuite, QuickBooks Online, Xerono first choiceZoho Booksno first choicenothing named
Four alternatives
BlackLine, Bluecopa, Oracle NetSuite, Vic.aiThree alternatives
FloQast, Pilot, Ramp AIThree alternatives
Bookeeping.ai, QuickBooks Online, WaveKimi K2Sage IntacctRamp Accounting Agent, ZeniChangedQuickBooks Online, XeroZoho Booksno first choiceagainst: Bench, Botkeeper, ChatGPT, Claude, ScaleFactor
Four alternatives
BILL, Oracle NetSuite, Ramp Accounting Agent, RilletTwo alternatives
Pilot, Vic.aiThree alternatives
Docyt, Puzzle, Vic.aiTwo alternatives
Booke AI, WaveGLM 4.7 FlashXSage Intacct, XeroDocytChangedZeniWaveno first choiceagainst: ChatGPT, Sage Copilot
Three alternatives
Oracle NetSuite, Ramp Accounting Agent, RilletThree alternatives
AppZen, BILL, Vic.aiThree alternatives
Botkeeper, Indy, PuzzleEight alternatives
BookWell, Booke AI, FreshBooks, Manus, QuickBooks Online, ReceiptsAI, SparkReceipt, XeroMiniMax M2.5Sage IntacctVic.aiChangedQuickBooks Online, Vic.ai, Xero, ZeniWaveno first choiceagainst: ChatGPT, Sage Copilot
Three alternatives
Booke AI, Oracle NetSuite, Vic.aiThree alternatives
BILL, Rillet, TrullionOne alternative
WaveTwo alternatives
FreshBooks, QuickBooks OnlineGPT-6 LunaSage Intacctagainst: Ramp Accounting AgentNumericChangedagainst: Sage Intacct Finance Intelligence AgentQuickBooks Online, XeroZoho Booksno first choicenothing named
Two alternatives
Intuit Enterprise Suite, Oracle NetSuiteTwo alternatives
Vic.ai, Workday's native Accounting AgentFive alternatives
Digits, Docyt, Puzzle, Sage Intacct, Zoho BooksTwo alternatives
QuickBooks Online, WaveMuse Glimmer 30BRilletRilletHeldQuickBooks Online with Intuit IntelligenceDigits, Zoho Booksagainst: QuickBooks Onlineno first choiceagainst: ChatGPT, Claude, DeepSeek, Grok, Meta AI
One alternative
Sage IntacctOne alternative
Ramp Accounting AgentNine alternatives
BILL, Botkeeper, Dext, FreshBooks, Numeric, Oracle NetSuite, Ramp Accounting Agent, Vic.ai, XeroTwo alternatives
Bench, Bookeeping.aiBold 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. Full answer text is in the free responses file. Download the record
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 | 2026-10-01 10:12 | yes | 9 | 7 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:02 | yes | 4 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:25 | yes | 24 | 24 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 09:36 | yes | 20 | 4 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:46 | yes | 20 | 7 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:25 | yes | 5 | 3 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:25 | yes | 22 | 34 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:38 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 08:39 | yes | 19 | 74 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 07:39 | yes | 17 | 24 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 09:55 | yes | 16 | 20 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:39 | yes | 12 | 28 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 09:16 | yes | 4 | 19 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:07 | yes | 20 | 26 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:28 | yes | 17 | 9 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:01 | yes | 4 | 7 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:03 | yes | 9 | 18 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 07:36 | yes | 17 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:26 | yes | 24 | 8 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 09:59 | yes | 5 | 3 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 11:08 | yes | 20 | 26 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:04 | yes | 10 | 6 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 10:26 | yes | 9 | 18 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:03 | yes | 20 | 28 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:13 | yes | 15 | 27 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 08:31 | yes | 10 | 29 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 09:07 | yes | 4 | 15 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:28 | yes | 17 | 25 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:10 | yes | 9 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 07:54 | yes | 4 | 7 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:45 | yes | 16 | 23 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 08:17 | yes | 20 | 6 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:26 | yes | 21 | 7 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:49 | yes | 25 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:09 | yes | 22 | 40 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:04 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 08:21 | yes | 5 | 24 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:31 | yes | 19 | 26 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:53 | yes | 25 | 41 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:24 | yes | 24 | 26 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:06 | yes | 7 | 27 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:30 | yes | 15 | 33 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:41 | yes | 9 | 8 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:47 | yes | 5 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:48 | yes | 9 | 19 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 11:21 | yes | 17 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:01 | yes | 24 | 7 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 10:32 | yes | 5 | 3 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:31 | yes | 24 | 26 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 11:22 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:20 | yes | 20 | 39 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:37 | yes | 14 | 31 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:00 | yes | 19 | 126 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:13 | yes | 9 | 13 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:52 | yes | 4 | 16 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:41 | yes | 25 | 34 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 10:28 | no | 0 | 7 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:15 | no | 0 | 8 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:58 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 09:41 | yes | 16 | 6 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:37 | yes | 13 | 13 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:31 | no | 0 | 8 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:58 | yes | 23 | 33 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:52 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:39 | no | 0 | 25 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:05 | yes | 13 | 38 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 09:03 | yes | 15 | 12 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 08:41 | no | 0 | 10 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:24 | yes | 3 | 14 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:14 | yes | 13 | 26 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 09:25 | yes | 16 | 11 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 09:12 | yes | 4 | 6 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:08 | yes | 19 | 25 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 08:03 | yes | 20 | 5 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:19 | yes | 24 | 8 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 08:57 | yes | 5 | 4 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 08:40 | yes | 25 | 40 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 11:03 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 10:14 | no | 0 | 39 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:43 | yes | 23 | 27 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:41 | yes | 24 | 80 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:25 | yes | 23 | 29 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:54 | yes | 2 | 18 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:19 | yes | 25 | 37 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
Acumatica read as Acumatica Cloud ERP
Bench Accounting read as Bench
Bill.com read as BILL
Intuit QuickBooks read as QuickBooks Online
NetSuite read as Oracle NetSuite
QuickBooks read as QuickBooks Online
QuickBooks (Intuit Assist) read as QuickBooks Online
QuickBooks (Intuit) read as QuickBooks Online
QuickBooks Free read as QuickBooks Online
QuickBooks 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
Aura
Fazeshift's accounts receivable agents
Hyperbots
Intuit AI
Intuit Enterprise Suite's accounting agent
Manus (AI Receipt Tracker)
Microsoft 365 Copilot
OCTA
Papertools
Ramp AI
ReceiptsAI
ReceiptsBot
Sage Intacct Finance Intelligence Agent
ScaleFactor
SparkReceipt
Spotlight
Vuuv
Workday's native Accounting Agent
ZENI.AI
Discontinued, still offered
No shut-down product was recommended here.