Account reconciliation
Asked as “account reconciliation software”, and as “bank reconciliation automation”, on behalf of a mid-market B2B company. 49 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Standing · first-choice share
33%
Contested · Numeric 14%
33FloQast14Numeric10QuickBooks Online43others
33% 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 three 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.
All twenty-eight head-to-head pages: the top eight products, each against each
FloQast vs Zoho BooksFloQast vs HighRadiusFloQast vs XeroFloQast vs Prophix OneNumeric vs Trintech AdraNumeric vs QuickBooks OnlineNumeric vs Zoho BooksNumeric vs HighRadiusNumeric vs XeroNumeric vs Prophix OneTrintech Adra vs QuickBooks OnlineTrintech Adra vs Zoho BooksTrintech Adra vs HighRadiusTrintech Adra vs XeroTrintech Adra vs Prophix OneQuickBooks Online vs Zoho BooksQuickBooks Online vs HighRadiusQuickBooks Online vs XeroQuickBooks Online vs Prophix OneZoho Books vs HighRadiusZoho Books vs XeroZoho Books vs Prophix OneHighRadius vs XeroHighRadius vs Prophix OneXero vs Prophix One
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
11Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative50%
Key
01FloQast33%
FloQast33%02Numeric14%
Numeric14%03Trintech Adra10%
Trintech Adra10%04QuickBooks Online10%
QuickBooks Online10%05Zoho Books6%
Zoho Books6%06HighRadius4%
HighRadius4%07Xero4%
Xero4%08Prophix One2%
Prophix One2%09ReconArt0%
ReconArt0%10Trintech0%
Trintech0%11BlackLine Transaction Matching0%
BlackLine Transaction Matching0%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.
BlackLine Transaction Matching44%
17 of 39 labels negative · 8 of 12 models · 2 hard negative
“smaller/mid-market users often complain it *complicates* prep work, has steep implementation, high costs, and doesn't save time” Grok 4.20, negative prompt
FloQast9%
4 of 44 labels negative · 4 of 12 models
“only if you're a growing accounting team that can justify a custom-priced close/reconciliation platform; it does not publish simple per-user pricing” GPT-5.4 mini, budget prompt
Microsoft Excel100%
3 of 3 labels negative · 3 of 12 models · 2 hard negative
“Excel should be actively phased out of your primary reconciliation workflow” Gemini 3.5 Flash, negative prompt
Automation Anywhere100%
2 of 2 labels negative · 2 of 12 models · 1 hard negative
“custom RPA bots (using platforms like UiPath or Automation Anywhere) ... the RPA bot breaks” Gemini 3.5 Flash, negative 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. 813 links across 161 sites, every framing counted. Ranked by the number of answers carrying the site or page.
vendor site · Numeric44 answers · 57 citations · 11 models
vendor site · HighRadius32 answers · 56 citations · 11 models
vendor site · Prophix27 answers · 30 citations · 11 models
vendor site · Ramp25 answers · 25 citations · 11 models
vendor site · Bluecopa24 answers · 27 citations · 8 models
vendor site · Worldmetrics21 answers · 27 citations · 9 models
vendor site · Maxima20 answers · 23 citations · 9 models
vendor site · Airwallex20 answers · 20 citations · 10 models
17 answers · 17 citations · 9 models
16 answers · 16 citations · 10 models
vendor site · Reconciler15 answers · 16 citations · 8 models
15 answers · 15 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.
40 answers · 11 models
27 answers · 10 models
26 answers · 10 models
25 answers · 11 models
20 answers · 8 models
18 answers · 9 models
17 answers · 9 models
16 answers · 10 models
15 answers · 9 models
14 answers · 6 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 “account reconciliation software”, “best account reconciliation software”, “reconciliation tools”. 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 |
|---|---|---|---|---|---|---|---|---|
| FloQast floqast.com | 33% | 389 | 9,900 | 194 | 41,324 | $5,039 | 76 | |
| Numeric numeric.io | 14% | 201 | 12,100 | 38,006 | 94,254 | $426 | 9 | 4 |
| Trintech trintech.com Trintech Adra 10%, Trintech 0% | 10% | 134 | 1,900 | 44 | 30,370 | 13 | 2 | |
| QuickBooks quickbooks.ninja QuickBooks Online 10% | 10% | 692 | 1,000,000 | 54,681 | 253 company | |||
| Zoho zoho.com Zoho Books 6% | 6% | 367 | 27,100 | 268 | 1,216,894 company | $51,031 | 119 | |
| HighRadius highradius.com | 4% | 604 | 6,600 | 118 | 294,561 | $2,272 | 120 | 1 |
| Xero xero.com | 4% | 729 | 90,500 | 4,610 | 1,200,289 | $500 | 119 | |
| Wave waveapps.com | 4% | 363 | 368,000 | 253,218 | 708,862 | 39 | ||
| Prophix prophix.com Prophix One 2% | 2% | 107 | 1,600 | 41 | 14,138 company | $109 | 103 | |
| Sage sage.com Sage Intacct 2% | 2% | 500 | 246,000 | 90,599 | 1,737,127 company | $114,671 | 78 |
Google's top ten for the three searches hold 15 sites; 4 of them are among the sites the models cited here (bluecopa.com, highradius.com, numeric.io, ramp.com). The first result for “account reconciliation software” is highradius.com.
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 account reconciliation software for a mid-market B2B company?”Paraphrase“Which bank reconciliation automation would you recommend to a mid-sized B2B company?”Comparative“What are the top reconciliation tools and how do they differ?”Budget-constrained“What is the best account reconciliation software for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating an account reconciliation software. What should we look at?”Negative“Which reconciliation tools should I avoid or be cautious about?”
Claude Haiku 4.5no first choiceTrintech AdraChangedno first choiceQuickBooks Onlineno first choicenothing named
Two alternatives
Numeric, Sage IntacctFour alternatives
ReconArt, Wave, Xero, Zoho BooksGPT-5.4 miniFloQastSage IntacctChangedBlackLine Transaction Matching, Trintech Cadencyagainst: Microsoft ExcelQuickBooks Online, Xeroagainst: BlackLine Transaction Matching, FloQastno first choicenothing named
Three alternatives
BlackLine Transaction Matching, Oracle Account Reconciliation Cloud, TrintechOne alternative
Oracle NetSuiteTwo alternatives
Duco, Oracle NetSuiteOne alternative
Zoho BooksGemini 3.5 FlashNumeric, ZoneReconcileagainst: BlackLine Transaction Matching, QuickBooks Online, Trintech Cadency, XeroFloQast, NumericChangedagainst: BlackLine Transaction MatchingBlackLine Transaction MatchingJustPerformagainst: BlackLine Transaction Matching, FloQastFloQast, Numericagainst: BlackLine Transaction Matchingagainst: Automation Anywhere, BlackLine Transaction Matching, Microsoft Excel, Oracle NetSuite, PayPal, QuickBooks Online, SAP Reconciliation, Shopify Payments, Stripe, Trintech, UiPath
Three alternatives
FloQast, HighRadius, Trintech AdraTwo alternatives
HighRadius, Trintech AdraFive alternatives
FloQast, HighRadius, Numeric, ReconArt, SolveXiaFive alternatives
NCH Express Accounts, QuickBooks Online, ReconArt, Xero, Zoho BooksOne alternative
Trintech AdraPerplexity SonarFloQastagainst: BlackLine Transaction MatchingFloQast, Trintech AdraChangedBlackLine Transaction MatchingQuickBooks Onlineno first choicenothing named
Two alternatives
Numeric, Prophix OneThree alternatives
BlackLine Transaction Matching, Tesorio, Vic.aiSeven alternatives
Duco, FloQast, HighRadius, Numeric, ReconArt, SolveXia, TrintechThree alternatives
Wave, Xero, Zoho BooksGrok 4.20FloQastagainst: BlackLine Transaction MatchingFloQastHeldBlackLine Transaction MatchingWaveagainst: GnuCashno first choiceagainst: BlackLine Transaction Matching, Docyt, Embat, FloQast, Oracle Account Reconciliation Cloud
Three alternatives
Numeric, Prophix One, Trintech AdraFour alternatives
BlackLine Transaction Matching, HighRadius, ReconArt, Trintech AdraSix alternatives
FloQast, HighRadius, QuickBooks Online, ReconArt, Trintech, XeroTwo alternatives
QuickBooks Online, XeroMistral SmallHighRadius, Prophix OneFloQast, NomentiaChangedno first choiceQuickBooks Onlineno first choicenothing named
Two alternatives
Sage Intacct, Trintech AdraTwo alternatives
HighRadius, Trintech AdraOne alternative
XeroDeepSeek V4 FlashNumericagainst: BlackLine Transaction MatchingFloQastChangedagainst: BlackLine Transaction Matching, Trintech AdraBlackLine Transaction Matching, TrintechZoho Booksagainst: WaveFloQast, Numeric, Trintech Adraagainst: BlackLine Transaction Matchingagainst: Automation Anywhere, UiPath
Two alternatives
FloQast, Trintech AdraFour alternatives
HighRadius, Numeric, Oracle NetSuite, Sage IntacctNine alternatives
FloQast, Hevo Data, IBM InfoSphere QualityStage, Informatica Data Quality, Oracle Enterprise Data Quality, ReconArt, SmartStream, Talend Data Quality, Trintech AdraThree alternatives
Ledgerler, NCH Express Accounts, XeroOne alternative
Sage IntacctLlama 4 Maverickno first choiceFloQast, US Tech Automations, Vic.aiChangedno first choiceZoho Booksno first choicenothing named
One alternative
RampQwen 3.7 FlashTrintech AdraFloQastChangedAico, FloQast, Workivaagainst: AlteryxQuickBooks Onlineno first choicenothing named
Three alternatives
FloQast, Numeric, Prophix OneFour alternatives
Oracle NetSuite, Sage Intacct, Tesorio, Vic.aiThree alternatives
HighRadius, Oracle Account Reconciliation Cloud, ReconArtTwo alternatives
Ramp, XeroKimi K2FloQast, NumericFloQastChangedagainst: AutoRek, BlackLine Transaction Matching, HighRadiusBlackLine Transaction MatchingZoho Booksagainst: NCH Express AccountsFloQastagainst: BlackLine Transaction Matching, Microsoft Excel, Xero
Two alternatives
Prophix One, Trintech AdraThree alternatives
Numeric, ReconArt, Trintech AdraThree alternatives
FloQast, Numeric, Trintech CadencyTwo alternatives
QuickBooks Online, WaveFour alternatives
BlackLine Transaction Matching, HighRadius, Numeric, TrintechGLM 4.7 FlashXNumericagainst: BlackLine Transaction MatchingHighRadiusChangedBlackLine Transaction MatchingXeroagainst: BlackLine Transaction Matching, FloQast, Trintechno first choicenothing named
Seven alternatives
FloQast, HighRadius, OneStream, Oracle Account Reconciliation Cloud, Prophix One, Ramp, Trintech AdraThree alternatives
FloQast, Nomentia, Sage IntacctFour alternatives
Bluecopa, FloQast, HighRadius, TrintechFour alternatives
QuickBooks Online, Sage Business Cloud Accounting, Wave, Zoho BooksMiniMax M2.5Trintech Adraagainst: Trintech CadencyFloQastChangedagainst: BlackLine Transaction MatchingBlackLine Transaction MatchingWaveagainst: NCH Express Accountsno first choicenothing named
Two alternatives
Numeric, RampTwo alternatives
HighRadius, NomentiaFive alternatives
FloQast, Oracle Fusion Cloud EPM, Oracle NetSuite, Trintech, VenaTwo alternatives
QuickBooks Online, 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 20:02 | yes | 9 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:23 | yes | 3 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 21:55 | yes | 16 | 69 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-09-17 18:23 | yes | 20 | 8 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 19:20 | yes | 24 | 14 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 18:20 | yes | 5 | 6 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 20:14 | yes | 17 | 19 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 20:55 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 19:57 | yes | 5 | 24 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:19 | yes | 8 | 22 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 20:23 | yes | 8 | 40 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 20:38 | yes | 5 | 45 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:53 | yes | 15 | 12 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:53 | yes | 2 | 6 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 17:57 | yes | 14 | 27 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-09-17 19:48 | yes | 20 | 6 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 17:53 | yes | 23 | 15 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 21:09 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 20:32 | yes | 18 | 18 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:28 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 20:55 | yes | 5 | 24 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 19:27 | yes | 15 | 21 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 19:44 | yes | 22 | 81 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 18:57 | yes | 9 | 18 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:50 | yes | 9 | 7 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 21:07 | yes | 4 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 21:54 | yes | 18 | 61 s |
| Comparative | Perplexity Sonar | sonar | 2026-09-17 18:31 | yes | 20 | 11 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 19:55 | yes | 24 | 13 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 19:42 | yes | 9 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 19:59 | yes | 18 | 23 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 19:18 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 19:44 | yes | 5 | 28 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:52 | yes | 10 | 22 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 17:57 | yes | 28 | 95 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 18:02 | yes | 9 | 27 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:00 | yes | 9 | 8 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:09 | yes | 2 | 8 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 19:28 | yes | 10 | 18 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-09-17 20:14 | yes | 20 | 5 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 19:40 | yes | 28 | 17 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 19:47 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 21:03 | yes | 10 | 10 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 19:58 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 20:45 | yes | 5 | 23 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:28 | yes | 14 | 27 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 18:15 | yes | 11 | 33 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:30 | yes | 13 | 36 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:56 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 20:21 | no | 0 | 7 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 18:24 | yes | 12 | 26 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-09-17 18:28 | 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 20:14 | yes | 16 | 11 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 18:42 | no | 0 | 8 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-17 19:01 | yes | 20 | 79 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:53 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 18:32 | yes | 5 | 26 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 18:53 | yes | 14 | 25 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 18:32 | yes | 8 | 61 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:58 | yes | 5 | 23 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-17 19:57 | no | 0 | 2 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-17 19:59 | no | 0 | 4 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-17 19:31 | yes | 12 | 22 s |
| Negative framing | Perplexity Sonar | sonar | 2026-09-17 18:42 | yes | 20 | 6 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 19:55 | yes | 37 | 15 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-09-17 20:51 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-17 19:53 | yes | 14 | 15 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-17 18:57 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-17 19:58 | no | 0 | 26 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-17 20:43 | yes | 19 | 37 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-17 18:05 | yes | 19 | 98 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-17 19:43 | yes | 8 | 24 s |
Noise floor in this category
Flips between the edition run and its calibration repeat. Six prompts per model is a small sample; the index-wide floor is the number to trust.
ShowHide
Claude Haiku 4.5
3 of 4 flipped
GPT-5.4 mini
3 of 4 flipped
Gemini 3.5 Flash
3 of 5 flipped
Perplexity Sonar
2 of 4 flipped
Grok 4.20
2 of 5 flipped
Mistral Small
4 of 4 flipped
DeepSeek V4 Flash
3 of 5 flipped
Llama 4 Maverick
2 of 3 flipped
Qwen 3.7 Flash
3 of 4 flipped
Kimi K2
4 of 5 flipped
GLM 4.7 FlashX
4 of 4 flipped
MiniMax M2.5
3 of 4 flipped
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
Adra read as Trintech Adra
Adra by Trintech read as Trintech Adra
BlackLine read as BlackLine Transaction Matching
Excel read as Microsoft Excel
Hevo read as Hevo Data
NetSuite read as Oracle NetSuite
Prophix read as Prophix One
QuickBooks read as QuickBooks Online
SAP read as SAP Reconciliation
SAP Account Substantiation and Automation by BlackLine read as BlackLine Transaction Matching
Wave Accounting read as Wave
Zoho read as Zoho Books
Unresolved, counted raw
Great Expectations
IBM InfoSphere QualityStage
Informatica Data Quality
Oracle Enterprise Data Quality
Precisely Data360
Qntrl
Soda
Talend Data Quality
Discontinued, still offered
No shut-down product was recommended here.