Sales intelligence and contact data
Asked as “B2B contact data and sales intelligence platform”, and as “B2B prospecting database”, on behalf of a mid-market B2B company. 42 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Standing · first-choice share
76%
Clear leader
76Apollo.io17ZoomInfo SalesOS05UpLead02others
76% of first choices, clear leader.
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 nine 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 six head-to-head pages: the top four products, each against each
One product takes 76% of first choices here, so the chart would put twelve markers in one corner and one at the far edge. The two measurements it plots are columns in the standing above: share, and the negative label rate. Three products carry a negative rate above 25% in this category.
What they warned about
Ten of twelve models held their first choice under the paraphrase. Claude Haiku 4.5 and GPT-5.4 mini 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.
ZoomInfo SalesOS44%
27 of 61 labels negative · 11 of 12 models · 6 hard negative
“What to avoid on a tight budget - ZoomInfo, Cognism, 6sense, Demandbase — enterprise tools with opaque pricing” DeepSeek V4 Flash, budget prompt
Apollo.io16%
11 of 67 labels negative · 11 of 12 models · 3 hard negative
“Apollo’s "single-source" database approach often leads to high bounce rates... shares the same "scraping controversy" as Seamless.ai” Qwen 3.7 Flash, negative prompt
Lusha21%
10 of 48 labels negative · 9 of 12 models · 2 hard negative
“Has the lowest rating on Trustpilot of 1.3/5. Users report accuracy has declined, particularly for phone numbers” Claude Haiku 4.5, negative prompt
Seamless.AI53%
10 of 19 labels negative · 8 of 12 models · 7 hard negative
“Despite claiming 98% accuracy, independent community analysis and G2 reviews consistently place their actual email accuracy closer to 60–75%” Qwen 3.7 Flash, negative prompt
What they cite
Four of the twelve models returned a source list in this edition: four return the pages they cited.
Sites the answers cite
20 of 72 answers in this category came back with a source list, from 4 of 12 models: citations where the model returns them, or the search results it consulted. 253 links across 126 sites, every framing counted. Ranked by the number of answers carrying the site or page. The other 8 models searched through a gateway that returned no source list on this edition.
vendor site · Salesmotion9 answers · 11 citations · 3 models
vendor site · ZoomInfo8 answers · 15 citations · 2 models
vendor site · Autobound8 answers · 9 citations · 3 models
vendor site · Salesgenie8 answers · 8 citations · 3 models
vendor site · Demandbase6 answers · 7 citations · 2 models
vendor site · Amplemarket6 answers · 6 citations · 2 models
vendor site · Monday.com5 answers · 6 citations · 2 models
vendor site · Alpharun5 answers · 5 citations · 3 models
vendor site · Cognism4 answers · 7 citations · 2 models
vendor site · Saleshandy4 answers · 6 citations · 2 models
vendor site · Avoma4 answers · 4 citations · 3 models
vendor site · Cleanlist4 answers · 4 citations · 2 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.
7 answers · 3 models
5 answers · 3 models
5 answers · 2 models
5 answers · 2 models
5 answers · 2 models
4 answers · 2 models
4 answers · 3 models
4 answers · 1 model
4 answers · 2 models
3 answers · 1 model
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 “b2b contact data and sales intelligence platform”, “best b2b contact data and sales intelligence platform”. 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 |
|---|---|---|---|---|---|---|---|---|
| Apollo.io apollo.io | 76% | 1010 | 33,100 | 396 | 111,608 | 94 | 3 | |
| ZoomInfo parent site ZoomInfo SalesOS 17% | 17% | 193 | 135,000 | 1,810 | ||||
| UpLead uplead.com | 5% | 83 | 3,600 | 57 | 15,339 | 7 | ||
| Cognism cognism.com | 2% | 349 | 3,600 | 68 | 48,685 | 15 | ||
| Lusha lusha.com | 0% | 280 | 12,100 | 893 | 52,570 | $11 | 57 | |
| Clay clay.com | 0% | 287 | 135,000 | 168,089 | 294,056 | 11 | ||
| LinkedIn linkedin.com LinkedIn Sales Navigator 0% | 0% | 147 | 11,100,000 | 77,031 | 331,033,472 company | $1,032 | 113 | |
| Salesmotion salesmotion.io | 0% | 11 | 320 | 4 | 11,256 | |||
| Amplemarket amplemarket.com | 0% | 25 | 3,600 | 8 | 12,067 | 8 | ||
| Hunter hunter.io | 0% | 79 | 201,000 | 280,275 | 152,782 | 6 |
Google's top ten for the two searches hold 11 sites; 4 of them are among the sites the models cited here (autobound.ai, demandbase.com, pipeline.zoominfo.com, salesgenie.com). The first result for “b2b contact data and sales intelligence platform” is autobound.ai.
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 B2B contact data and sales intelligence platform for a mid-market B2B company?”Paraphrase“Which B2B prospecting database would you recommend to a mid-sized B2B company?”Comparative“What are the top sales intelligence and contact data platforms and how do they differ?”Budget-constrained“What is the best B2B contact data and sales intelligence platform for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a B2B contact data and sales intelligence platform. What should we look at?”Negative“Which sales intelligence and contact data platforms should I avoid or be cautious about?”
Claude Haiku 4.5Apollo.iono first choiceChangedagainst: ZoomInfo SalesOSZoomInfo SalesOSagainst: BomboraUpLeadno first choiceagainst: Apollo.io, Lusha, SalesIntel, ZoomInfo SalesOS
Three alternatives
Amplemarket, Lead411, ZoomInfo SalesOSThree alternatives
Apollo.io, Clay, CognismFour alternatives
Apollo.io, Kaspr, Lead411, LushaGPT-5.4 miniApollo.io, ZoomInfo SalesOSCognismChangedApollo.ioagainst: Seamless.AIApollo.io, UpLeadagainst: ZoomInfo SalesOSno first choiceagainst: Mobilewalla
One alternative
CognismOne alternative
ZoomInfo SalesOSFive alternatives
Cognism, LinkedIn Sales Navigator, Lusha, UpLead, ZoomInfo SalesOSGemini 3.5 FlashApollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldagainst: ZoomInfo SalesOSApollo.io, ZoomInfo SalesOSApollo.ioagainst: Cognism, ZoomInfo SalesOSno first choiceagainst: Apollo.io, Cognism, Lusha, People Data Labs, ZoomInfo SalesOS
Three alternatives
Clay, Cognism, UpLeadThree alternatives
Clay, Cognism, UpLeadFive alternatives
6sense Sales Intelligence, Clay, Cognism, Demandbase, LinkedIn Sales NavigatorThree alternatives
Kaspr, Lusha, UpLeadFour alternatives
Apollo.io, Cognism, Lusha, ZoomInfo SalesOSPerplexity SonarApollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldApollo.io, ZoomInfo SalesOSApollo.iono first choiceagainst: 6sense Sales Intelligence, Apollo.io, Gong, Seamless.AI, ZoomInfo SalesOS
Two alternatives
Cognism, UpLeadFour alternatives
Cognism, Lusha, UpLead, ZoomInfo SalesOSSix alternatives
6sense Sales Intelligence, Bombora, Cognism, Demandbase, Gong, LinkedIn Sales NavigatorThree alternatives
Hunter, Lusha, UpLeadGrok 4.20Apollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldZoomInfo SalesOSApollo.ioagainst: Cognism, ZoomInfo SalesOSZoomInfo SalesOSagainst: Apollo.io, Lusha, SalesIntel, Seamless.AI, ZoomInfo SalesOS
Three alternatives
Cognism, Lead411, UpLeadFour alternatives
Cognism, Lusha, UpLead, ZoomInfo SalesOSFour alternatives
6sense Sales Intelligence, Apollo.io, Cognism, LushaFour alternatives
Lead411, LeadIQ, Lusha, Saleshandy Lead FinderFive alternatives
6sense Sales Intelligence, Apollo.io, Bombora, Cognism, LushaMistral SmallApollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldZoomInfo SalesOSApollo.ioZoomInfo SalesOSagainst: Apollo.io, Cognism, Dun & Bradstreet, Lusha, Seamless.AI, ZoomInfo SalesOS
Four alternatives
Cognism, Lusha, Salesmotion, UpLeadThree alternatives
Cognism, UpLead, ZoomInfo SalesOSSix alternatives
6sense Sales Intelligence, Apollo.io, Bombora, Cognism, LinkedIn Sales Navigator, SalesmotionTwo alternatives
Hunter, Seamless.AIThree alternatives
Apollo.io, Cognism, SalesmotionDeepSeek V4 FlashApollo.ioApollo.ioHeldagainst: LushaApollo.io, Cognism, ZoomInfo SalesOSApollo.ioagainst: 6sense Sales Intelligence, Cognism, Demandbase, Seamless.AI, UpLead, ZoomInfo SalesOSno first choiceagainst: 6sense Sales Intelligence, Demandbaseagainst: 6sense Sales Intelligence, Apollo.io, RocketReach, Seamless.AI, ZoomInfo SalesOS
Three alternatives
Cognism, Lusha, ZoomInfo SalesOSFour alternatives
Cognism, Saleshandy Lead Finder, UpLead, ZoomInfo SalesOSSix alternatives
6sense Sales Intelligence, Bombora, Clay, LinkedIn Sales Navigator, Lusha, SalesmotionSeven alternatives
Hunter, LeadIQ, Lusha, Prospeo, RocketReach, Skrapp.io, Snov.ioSix alternatives
Apollo.io, Cognism, Lusha, SalesIntel, UpLead, ZoomInfo SalesOSLlama 4 MaverickZoomInfo SalesOSZoomInfo SalesOSHeldno first choiceApollo.ioZoomInfo SalesOSagainst: 6sense Sales Intelligence, Apollo.io, Lusha, ZoomInfo SalesOS
Three alternatives
Cognism, Salesloft, UpLeadThree alternatives
Apollo.io, Skrapp.io, UpLeadQwen 3.7 FlashApollo.ioApollo.ioHeldApollo.io, ZoomInfo SalesOSApollo.iono first choiceagainst: Seamless.AIagainst: Apollo.io, Proxycurl, Seamless.AI
Three alternatives
HubSpot Breeze Intelligence, Lusha, ZoomInfo SalesOSTwo alternatives
UpLead, ZoomInfo SalesOSFive alternatives
6sense Sales Intelligence, Amplemarket, Clay, Cognism, SalesmotionOne alternative
LushaKimi K2Apollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldagainst: ZoomInfo SalesOSno first choiceApollo.ioApollo.ioagainst: ZoomInfo SalesOSagainst: Apollo.io, Cognism, Kaspr, Lusha, Seamless.AI, ZoomInfo SalesOS
Two alternatives
Cognism, UpLeadThree alternatives
Cognism, Lusha, UpLeadNine alternatives
6sense Sales Intelligence, Amplemarket, Apollo.io, Clay, Cognism, Demandbase, Gong, LinkedIn Sales Navigator, ZoomInfo SalesOSFour alternatives
Hunter, Lusha, RocketReach, Seamless.AIFour alternatives
Clay, Cognism, Lusha, SalesmotionGLM 4.7 FlashXApollo.ioagainst: Seamless.AI, ZoomInfo SalesOSApollo.ioHeldagainst: ZoomInfo SalesOSAmplemarketApollo.iono first choiceagainst: 11x, Apollo.io, Lusha, ZoomInfo SalesOS
Two alternatives
Lusha, UpLeadOne alternative
UpLeadSeven alternatives
6sense Sales Intelligence, Apollo.io, Clay, Cognism, Demandbase, Lusha, ZoomInfo SalesOSFour alternatives
Hunter, Lusha, RocketReach, UpLeadMiniMax M2.5Apollo.ioagainst: ZoomInfo SalesOSApollo.ioHeldApollo.io, ZoomInfo SalesOSApollo.ioagainst: Lusha, ZoomInfo SalesOSZoomInfo SalesOSagainst: Apollo.io, Lusha, ZoomInfo SalesOS
Four alternatives
6sense Sales Intelligence, Cognism, Lead411, LinkedIn Sales NavigatorThree alternatives
Cognism, UpLead, ZoomInfo SalesOSFive alternatives
6sense Sales Intelligence, Clay, Cognism, Lusha, SalesmotionOne alternative
LeadIQThree alternatives
Apollo.io, Cognism, G2 Buyer IntentBold 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 | 2026-09-15 00:41 | yes | 8 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 04:14 | yes | 4 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-14 23:15 | yes | 22 | 26 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-09-15 04:38 | yes | 20 | 4 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) | 2026-09-15 04:16 | yes | 0 | 12 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 03:12 | yes | 0 | 8 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-14 23:45 | yes | 0 | 21 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-14 23:12 | yes | 0 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-14 23:02 | no | 0 | 28 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-14 23:59 | yes | 0 | 32 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 02:29 | yes | 0 | 43 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-14 23:38 | yes | 0 | 16 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 02:35 | no | 0 | 5 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 01:46 | yes | 4 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 02:32 | yes | 6 | 18 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-09-15 01:51 | 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) | 2026-09-15 03:34 | yes | 0 | 7 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 04:47 | yes | 0 | 8 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-14 23:46 | yes | 0 | 16 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 00:47 | yes | 0 | 1 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 00:28 | yes | 0 | 24 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-14 23:07 | yes | 0 | 39 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-14 23:23 | yes | 0 | 16 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 01:16 | yes | 0 | 27 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 01:31 | yes | 9 | 9 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 03:40 | yes | 7 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 04:11 | yes | 19 | 24 s |
| Comparative | Perplexity Sonar | sonar | 2026-09-15 01:42 | yes | 20 | 9 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) | 2026-09-15 03:40 | yes | 0 | 6 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 03:09 | yes | 0 | 9 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-14 23:59 | yes | 0 | 59 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 02:48 | yes | 0 | 1 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 01:40 | yes | 0 | 31 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 01:42 | yes | 0 | 79 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 03:48 | yes | 0 | 112 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-14 23:28 | yes | 0 | 17 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-14 23:23 | yes | 7 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-14 23:23 | yes | 4 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 01:41 | yes | 9 | 17 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-09-15 00:08 | yes | 19 | 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) | 2026-09-15 02:27 | yes | 0 | 7 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 00:35 | yes | 0 | 9 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-15 03:25 | yes | 0 | 24 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 00:42 | yes | 0 | 1 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 02:13 | no | 0 | 37 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 02:30 | yes | 0 | 28 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 04:46 | yes | 0 | 110 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 04:03 | yes | 0 | 24 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 03:15 | no | 0 | 7 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-14 23:42 | no | 0 | 6 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-14 23:22 | no | 0 | 17 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-09-15 00:55 | yes | 20 | 8 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) | 2026-09-14 23:18 | yes | 0 | 8 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 04:16 | yes | 0 | 13 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-15 00:29 | yes | 0 | 42 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 02:18 | yes | 0 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 03:17 | no | 0 | 33 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 00:50 | yes | 0 | 52 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 03:25 | yes | 0 | 17 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 03:33 | yes | 0 | 15 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 03:04 | yes | 17 | 7 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-14 22:55 | yes | 5 | 6 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 00:58 | yes | 13 | 22 s |
| Negative framing | Perplexity Sonar | sonar | 2026-09-15 03:23 | yes | 20 | 8 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) | 2026-09-15 03:26 | yes | 0 | 7 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 02:45 | yes | 0 | 12 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via fireworks | 2026-09-15 04:58 | yes | 0 | 21 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 01:45 | yes | 0 | 2 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 01:37 | yes | 0 | 54 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 04:26 | yes | 0 | 80 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 02:07 | yes | 0 | 70 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-14 23:28 | yes | 0 | 19 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
4 of 4 flipped
Gemini 3.5 Flash
2 of 5 flipped
Perplexity Sonar
0 of 4 flipped
Grok 4.20
2 of 6 flipped
Mistral Small
2 of 6 flipped
DeepSeek V4 Flash
2 of 5 flipped
Llama 4 Maverick
1 of 4 flipped
Qwen 3.7 Flash
4 of 5 flipped
Kimi K2
3 of 6 flipped
GLM 4.7 FlashX
1 of 4 flipped
MiniMax M2.5
3 of 5 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
6sense read as 6sense Sales Intelligence
Skrapp read as Skrapp.io
ZoomInfo read as ZoomInfo SalesOS
ZoomInfo (SalesOS) read as ZoomInfo SalesOS
Unresolved, counted raw
Leadsimple
Proxycurl
Salesforce
Discontinued, still offered
No shut-down product was recommended here.