Knowledge base and self-service
Asked as “knowledge base software”, and as “customer self-service help center tool”, on behalf of a mid-market B2B company. 58 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
21%
Contested · Document360 17%
21Notion17Document36014Freshdesk48others
21% of first choices, contested.
Since September 2026▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Notion held the lead, +4 points on 18%, inside the 11-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
Notion41%Clear leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketNotion21%Contested▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.This pageEnterprise
Zendesk Guide28%Contested↗new leaderNew leader since September 2026: Confluence (28%) replaces Zendesk Guide (30% then, 26% now), 2 points clear, inside the 11-point floor.Standing →
Notion41%Clear leader▲+4Since September 2026: 38% → 42%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketNotion21%Contested▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.This pageEnterpriseZendesk Guide28%Contested↗new leaderNew leader since September 2026: Confluence (28%) replaces Zendesk Guide (30% then, 26% now), 2 points clear, inside the 11-point floor.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
01Notion21%30%50criticized challenger▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.18% → 22%
Notion21%30%50criticized challenger▲+4Since September 2026: 18% → 22%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.18% → 22%02
Document36017%2%42accepted challenger=heldSince September 2026: 14% → 14%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.14% → 14%
Document36017%2%42accepted challenger=heldSince September 2026: 14% → 14%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.14% → 14%03
Freshdesk14%4%23accepted challenger=heldSince September 2026: 12% → 12%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.12% → 12%
Freshdesk14%4%23accepted challenger=heldSince September 2026: 12% → 12%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.12% → 12%04Zendesk Guide7%10%40accepted challenger▲+2Since September 2026: 6% → 8%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.6% → 8%
Zendesk Guide7%10%40accepted challenger▲+2Since September 2026: 6% → 8%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.6% → 8%05
Confluence5%15%46accepted challenger▼−2Since September 2026: 6% → 4%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.6% → 4%
Confluence5%15%46accepted challenger▼−2Since September 2026: 6% → 4%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.6% → 4%06
Slite3%8%26accepted challenger▲+2Since September 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 4%
Slite3%8%26accepted challenger▲+2Since September 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 4%07
Helpjuice3%5%19accepted challenger=heldSince September 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 4%
Helpjuice3%5%19accepted challenger=heldSince September 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 4%08
HubSpot Service Hub3%0%10accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 4%
HubSpot Service Hub3%0%10accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 4%09
Guru2%7%28accepted challenger▼−2Since September 2026: 4% → 2%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 2%
Guru2%7%28accepted challenger▼−2Since September 2026: 4% → 2%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 2%10
Help Scout Docs2%6%18accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%
Help Scout Docs2%6%18accepted challenger▲+2Since September 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 2%11
ClickUp2%8%12accepted challenger=heldSince September 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 2%
ClickUp2%8%12accepted challenger=heldSince September 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 2%Show the one product at 0%, ordered by negative rate
12
Intercom Articles0%0%13accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%
Intercom Articles0%0%13accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%The floor is 11 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
Notion vs ConfluenceNotion vs SliteNotion vs HelpjuiceNotion vs HubSpot Service HubDocument360 vs FreshdeskDocument360 vs Zendesk GuideDocument360 vs ConfluenceDocument360 vs SliteDocument360 vs HelpjuiceDocument360 vs HubSpot Service HubFreshdesk vs Zendesk GuideFreshdesk vs ConfluenceFreshdesk vs SliteFreshdesk vs HelpjuiceFreshdesk vs HubSpot Service HubZendesk Guide vs ConfluenceZendesk Guide vs SliteZendesk Guide vs HelpjuiceZendesk Guide vs HubSpot Service HubConfluence vs SliteConfluence vs HelpjuiceConfluence vs HubSpot Service HubSlite vs HelpjuiceSlite vs HubSpot Service HubHelpjuice vs HubSpot Service Hub
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 →
010203040506070809101112Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Notion21%
Notion21%02Document36017%
Document36017%03Freshdesk14%
Freshdesk14%04Zendesk Guide7%
Zendesk Guide7%05Confluence5%
Confluence5%06Slite3%
Slite3%07Helpjuice3%
Helpjuice3%08HubSpot Service Hub3%
HubSpot Service Hub3%09Guru2%
Guru2%10Help Scout Docs2%
Help Scout Docs2%11ClickUp2%
ClickUp2%12Intercom Articles0%
Intercom Articles0%What they warned about
Two of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, Gemini 3.5 Flash, Perplexity Sonar, Grok 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX, MiniMax M2.5 and Muse Glimmer 30B 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.
Notion30%
15 of 50 labels negative · 11 of 14 models · 1 hard negative
“it falls short as a dedicated knowledge base due to its weak search, lack of version control, and missing customer-focused features” Llama 4 Maverick, negative prompt
Confluence15%
7 of 46 labels negative · 5 of 14 models
“Search issues: Surfaces archived pages above current ones ... Cost creep: Atlassian pricing changes have frustrated many users” Kimi K2, negative prompt
Zendesk Guide10%
4 of 40 labels negative · 4 of 14 models
“typical enterprise tools (like Zendesk or Salesforce) are often too expensive” Gemini 3.5 Flash, budget prompt
SharePoint60%
3 of 5 labels negative · 3 of 14 models
“notoriously complex to set up. It often requires a dedicated SharePoint administrator” 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
73 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. 949 links across 227 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.
38 answers · 43 citations · 13 models
vendor site · Slite34 answers · 48 citations · 11 models
20 answers · 32 citations · 10 models
vendor site · HubSpot20 answers · 25 citations · 11 models
vendor site · Plain17 answers · 20 citations · 11 models
vendor site · Helpjuice17 answers · 18 citations · 8 models
vendor site · Zendesk16 answers · 23 citations · 9 models
vendor site · Document36015 answers · 18 citations · 10 models
vendor site · MangoApps15 answers · 15 citations · 8 models
vendor site · BoldDesk14 answers · 14 citations · 7 models
vendor site · KnowledgeOwl14 answers · 14 citations · 8 models
vendor site · Helply13 answers · 20 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.
32 answers · 11 models
30 answers · 12 models
16 answers · 8 models
15 answers · 8 models
14 answers · 9 models
14 answers · 7 models
13 answers · 10 models
10 answers · 9 models
10 answers · 6 models
10 answers · 7 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 “best knowledge base software”, “knowledge base software”. 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 |
|---|---|---|---|---|---|---|---|---|
| Notion notion.com | 21% | 209 | 673,000 | 15,608 | 1,061,466 | 52 | ||
| Document360 document360.com | 17% | 105 | 1,300 | 20 | 15,294 | $648 | 92 | |
| Freshworks freshworks.com Freshdesk 14% | 14% | 283 | 12,100 | 391 | 111,586 company | $14,486 | 113 | |
| Zendesk Guide zendesk.com Zendesk Guide 7%, Zendesk for Customer Service 2% | 9% | 99 | 210 | 1 | 5,365,445 | $16,181 | 63 | |
| Atlassian atlassian.com Confluence 5% | 5% | 130 | 165,000 | 6,617 | 4,724,388 company | $5,906 | 61 | 4 |
| Pylon usepylon.com | 5% | 37 | 40,500 | 3,118 | 29,726 | $166 | 21 | |
| Slite slite.com | 3% | 70 | 2,900 | 70 | 38,045 | 1 | 1 | |
| Helpjuice helpjuice.com | 3% | 48 | 1,300 | 7 | 53,814 | 4 | ||
| HubSpot parent site HubSpot Service Hub 3% | 3% | 235 | 368,000 | 9,776 | ||||
| BookStack bookstackapp.com | 3% | 23 | 12,100 | 98 | 9,396 |
Google's top ten for the two searches hold 16 sites; 2 of them are among the sites the models cited here (g2.com, slite.com). The first result for “best knowledge base software” is ferndesk.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 knowledge base software for a mid-market B2B company?”Paraphrase“Which customer self-service help center tool would you recommend to a mid-sized B2B company?”Comparative“What are the top knowledge base tools and how do they differ?”Budget-constrained“What is the best knowledge base software for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a knowledge base software. What should we look at?”Negative“Which knowledge base tools should I avoid or be cautious about?”
Claude Haiku 4.5Document360, HelpjuiceFreshdesk, Help Scout DocsChangedNotionBookStack, Notionno first choicenothing named
Six alternatives
BlueTweak, Helply, KnowledgeOwl, Nuclino, Stonly, Zendesk GuideThree alternatives
Enjo, Zendesk Guide, Zoho DeskFive alternatives
Confluence, Document360, Guru, Help Scout Docs, Zendesk GuideThree alternatives
Groove, Nuclino, Zoho DeskGPT-5.4 miniZendesk Guideagainst: NotionZendesk GuideHeldIntercom Articles, Zendesk GuideNotionagainst: Document360, HelpCenter.io, Helpjuiceno first choicenothing named
Three alternatives
Confluence, Document360, GuruThree alternatives
Freshdesk, Help Scout Docs, Intercom ArticlesSix alternatives
Confluence, Document360, Guru, Microsoft Discovery Bookshelf / Knowledge Bases, Slab, TettraTwo alternatives
ClickUp, ConfluenceGemini 3.5 FlashDocument360, Guruagainst: Salesforce KnowledgeDocument360Changedno first choiceNotion, Slabagainst: Salesforce, Zendesk GuideGleanagainst: Confluence, Notionagainst: Confluence, Dropbox, Evernote, GitBook, Google Drive, MediaWiki, Notion, OneDrive, SharePoint
Six alternatives
Confluence, Glean, HubSpot Service Hub, Notion, Stonly, Zendesk GuideFour alternatives
Help Scout Docs, HubSpot Service Hub, Stonly, Zendesk GuideSeven alternatives
Confluence, Document360, Glean, Guru, Notion, Slite, Zendesk GuideFour alternatives
BookStack, Confluence, Mintlify, Zoho DeskThree alternatives
Document360, Guru, HelpjuicePerplexity SonarPylonFreshdeskChangedno first choiceNuclinono first choiceagainst: Confluence, Guru, Notion, Slite, Tettra
Three alternatives
Confluence, Document360, HelpjuiceFour alternatives
HubSpot Service Hub, Intercom Articles, Zendesk Guide, Zoho DeskTwo alternatives
BookStack, ProProfs Knowledge BaseGrok 4.1 FastConfluence, Document360Zendesk GuideChangedNotionBookStack, Notionagainst: Confluence, GitBook, Help Scout Docsno first choiceagainst: Confluence, Freshdesk, Notion, QnA Maker
One alternative
NotionFour alternatives
Freshdesk, Help Scout Docs, HubSpot Service Hub, Intercom ArticlesTwo alternatives
Confluence, Document360One alternative
OutlineFive alternatives
Document360, Guru, MangoApps, Slite, TettraMistral SmallDocument360TeamSupport, Zendesk GuideChangedno first choiceagainst: NotionNotionno first choiceagainst: BookStack, Notion, Obsidian, Tettra, Zendesk Guide
Three alternatives
Freshdesk, Notion, PylonTwo alternatives
Help Scout Docs, VivantioFour alternatives
BlueSpice, BookStack, ClickUp, HelpDocsDeepSeek V4 FlashHelpjuiceagainst: NotionFreshdeskChangedagainst: Zendesk GuideDocument360Notionno first choicenothing named
Five alternatives
Confluence, Document360, Freshdesk, Slite, Zendesk GuideThree alternatives
Help Scout Docs, HubSpot Service Hub, Intercom ArticlesSeven alternatives
Bloomfire, Confluence, Guru, Notion, Slite, Zendesk Guide, Zoho DeskFour alternatives
Confluence, GitBook, Nuclino, SliteLlama 4 MaverickPylonHubSpot Service HubChangedno first choiceNotionSliteagainst: Notionagainst: Confluence, Notion, Slite
Four alternatives
Document360, Freshdesk, Spekit, StonlyOne alternative
FreshdeskOne alternative
Help Scout DocsThree alternatives
Confluence, Document360, Zendesk GuideQwen 3.7 FlashDocument360against: ServiceNow Knowledge ManagementZendesk for Customer ServiceChangedno first choiceDocument360, Notionno first choiceagainst: Notionagainst: BambooHR’s Knowledge Base, ClickUp, Discord, Jira, Monday.com, Notion, Slack, WordPress
Four alternatives
Confluence, Freshdesk Knowledge Base, Notion, Zendesk GuideTwo alternatives
Freshdesk, HubSpot Service HubEight alternatives
ClickUp, Coda, Confluence, Freshdesk, HelpCrunch, Notion, Slite, Zendesk GuideFive alternatives
GitBook, GitLab, Slite, Wiki.js, Zoho DocsKimi K2Confluence, Freshdeskagainst: Zendesk GuideFreshdeskChangedno first choiceNotionno first choiceagainst: Bloomfire, Confluence, Guru, Notion, ServiceNow Knowledge Bases, SharePoint
Two alternatives
Notion, SliteThree alternatives
Document360, HubSpot Service Hub, Intercom ArticlesFive alternatives
Confluence, Document360, Guru, Notion, Zendesk GuideThree alternatives
ClickUp, Confluence, Help Scout DocsGLM 4.7 FlashXSliteFreshdeskChangedDocument360Notionno first choiceagainst: Google Drive, OneDrive, SharePoint
Five alternatives
Confluence, Document360, Guru, Help Scout Docs, NotionTwo alternatives
Help Scout Docs, Intercom ArticlesEight alternatives
Bloomfire, Confluence, Ferndesk, Guru, Help Scout Docs, HelpDocs, Notion, Zendesk GuideSix alternatives
BookStack, Confluence, Help Scout Docs, Nuclino, Slab, Wiki.jsMiniMax M2.5TettraHubSpot Service HubChangedno first choiceClickUp, Notionno first choiceagainst: Notion
Two alternatives
Confluence, Document360Two alternatives
Freshdesk, Zendesk GuideTwo alternatives
Confluence, KnowledgeBaseGPT-6 LunaDocument360Document360HeldConfluence, NotionSlabagainst: Notionno first choicenothing named
Three alternatives
Confluence, Guru, Zendesk GuideTwo alternatives
Intercom Articles, Zendesk GuideFour alternatives
Document360, GitBook, Guru, Zendesk GuideOne alternative
BookStackMuse Glimmer 30BDocument360, Freshdesk, PylonFreshdeskChangedPlainConfluence, Notionno first choicenothing named
Two alternatives
Confluence, LiveAgentThree alternatives
Document360, HelpDocs, PylonSeven alternatives
Confluence, Document360, Guru, Help Scout Docs, Helpjuice, Notion, Zendesk GuideThree alternatives
Guru, HelpDocs, HelpjuiceBold 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 12:24 | yes | 9 | 9 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 07:37 | yes | 5 | 7 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:21 | yes | 22 | 59 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 13:18 | yes | 25 | 3 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:11 | yes | 23 | 9 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:45 | yes | 5 | 3 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:57 | yes | 24 | 31 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 07:30 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 11:19 | yes | 9 | 22 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:26 | yes | 17 | 24 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:27 | yes | 21 | 43 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:21 | yes | 13 | 30 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 12:31 | yes | 4 | 17 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:47 | yes | 17 | 19 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 13:24 | yes | 10 | 7 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:18 | yes | 3 | 7 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 12:55 | yes | 13 | 23 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 09:17 | yes | 21 | 5 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:06 | yes | 25 | 8 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:27 | yes | 5 | 4 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 09:29 | yes | 20 | 15 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 09:41 | yes | 5 | 1 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 10:49 | yes | 9 | 26 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 07:43 | yes | 14 | 25 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 12:57 | yes | 23 | 265 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 07:26 | yes | 10 | 22 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 08:02 | yes | 3 | 17 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:39 | yes | 15 | 17 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:30 | yes | 9 | 7 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:22 | yes | 1 | 7 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:06 | yes | 13 | 23 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 13:40 | yes | 21 | 7 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 09:48 | yes | 22 | 9 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:52 | yes | 10 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:51 | yes | 23 | 54 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 13:15 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 13:42 | yes | 5 | 19 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 07:59 | yes | 19 | 20 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:26 | yes | 19 | 47 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:04 | yes | 18 | 39 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:18 | yes | 6 | 24 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:05 | yes | 12 | 22 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:21 | yes | 9 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:00 | yes | 3 | 8 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:18 | yes | 14 | 24 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 09:38 | yes | 17 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 12:01 | yes | 19 | 8 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 12:11 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:24 | yes | 23 | 25 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 13:54 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 13:32 | no | 0 | 37 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:43 | yes | 12 | 16 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:35 | yes | 15 | 25 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 08:18 | yes | 11 | 23 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 12:20 | yes | 3 | 7 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 10:26 | yes | 13 | 19 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 14:11 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 12:16 | no | 0 | 11 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:15 | yes | 10 | 23 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 11:39 | yes | 18 | 5 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 13:28 | yes | 13 | 7 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 10:24 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 10:22 | yes | 16 | 30 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:58 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 10:51 | no | 0 | 28 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 07:26 | yes | 10 | 15 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:04 | no | 0 | 14 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:43 | yes | 5 | 15 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:31 | yes | 3 | 20 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:09 | no | 0 | 2 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:02 | no | 0 | 3 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 13:59 | no | 0 | 3 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 12:38 | yes | 30 | 26 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 11:37 | yes | 25 | 4 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 10:04 | yes | 22 | 7 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 12:03 | yes | 5 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 13:17 | no | 0 | 4 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 10:11 | yes | 5 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 08:18 | yes | 17 | 49 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 10:57 | yes | 23 | 20 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:21 | yes | 19 | 67 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:17 | yes | 14 | 32 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 10:58 | yes | 2 | 9 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 11:15 | no | 0 | 4 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
Help Scout read as Help Scout Docs
Help Scout (Docs) read as Help Scout Docs
HubSpot read as HubSpot Service Hub
Intercom read as Intercom Articles
Intercom (Fin) read as Intercom Articles
ServiceNow read as ServiceNow Knowledge Management
Zendesk read as Zendesk Guide
Unresolved, counted raw
BambooHR’s Knowledge Base
Bear
BlueTweak
Freshdesk Knowledge Base
GitLab
Intercom Guide
Jet Admin
Microsoft Discovery Bookshelf / Knowledge Bases
QnA Maker
Salesforce
Stency
Theneo
Vivantio
Zoho Docs
livepro
Discontinued, still offered
No shut-down product was recommended here.