B2B intent data providers
Asked as “B2B intent data provider”, and as “B2B buyer intent data vendor”, on behalf of a mid-market B2B company. 56 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
27Apollo.io27Bombora12Dealfront34others
27% of first choices, contested.
Since September 2026↗new leaderNew leader since September 2026: Apollo.io (29%) replaces Bombora (35% then, 25% now), 4 points clear, inside the 11-point floor.Apollo.io leads at 29%, replacing Bombora, which led at 35% and stands at 25% now: 4 points clear, inside the floor, so the swap reads as unsettled.
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
Apollo.io65%Clear leader▲+10Since September 2026: 56% → 65%, +10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketApollo.io27%Contested↗new leaderNew leader since September 2026: Apollo.io (29%) replaces Bombora (35% then, 25% now), 4 points clear, inside the 11-point floor.This pageEnterprise
6sense44%Clear leader=heldSince September 2026: 45% → 45%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →
Apollo.io65%Clear leader▲+10Since September 2026: 56% → 65%, +10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.Standing →Mid-marketApollo.io27%Contested↗new leaderNew leader since September 2026: Apollo.io (29%) replaces Bombora (35% then, 25% now), 4 points clear, inside the 11-point floor.This pageEnterprise6sense44%Clear leader=heldSince September 2026: 45% → 45%, ±0 points. Inside the 11-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
01Apollo.io27%6%36accepted challenger▲+4Since September 2026: 25% → 29%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.25% → 29%
Apollo.io27%6%36accepted challenger▲+4Since September 2026: 25% → 29%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.25% → 29%02
Bombora27%27%66criticized challenger▼−10Since September 2026: 35% → 25%, −10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.35% → 25%
Bombora27%27%66criticized challenger▼−10Since September 2026: 35% → 25%, −10 points. Inside the 11-point floor: within noise. Read over the models both editions asked.35% → 25%03
Dealfront12%0%37accepted challenger▲+11Since September 2026: 2% → 12%, +11 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 12%
Dealfront12%0%37accepted challenger▲+11Since September 2026: 2% → 12%, +11 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 12%04
Factors.ai7%0%13accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 4%
Factors.ai7%0%13accepted challenger▲+4Since September 2026: 0% → 4%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 4%05
ZoomInfo7%36%50criticized challenger▲+4Since September 2026: 4% → 8%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 8%
ZoomInfo7%36%50criticized challenger▲+4Since September 2026: 4% → 8%, +4 points. Inside the 11-point floor: within noise. Read over the models both editions asked.4% → 8%06
RB2B5%0%14accepted challenger▲+2Since September 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 4%
RB2B5%0%14accepted challenger▲+2Since September 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 4%076sense5%41%64criticized challenger▲+6Since September 2026: 0% → 6%, +6 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 6%
6sense5%41%64criticized challenger▲+6Since September 2026: 0% → 6%, +6 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 6%08
G2 Buyer Intent2%11%44accepted challenger▼−11Since September 2026: 13% → 2%, −11 points. Past the 11-point floor: movement. Read over the models both editions asked.13% → 2%
G2 Buyer Intent2%11%44accepted challenger▼−11Since September 2026: 13% → 2%, −11 points. Past the 11-point floor: movement. Read over the models both editions asked.13% → 2%09
Lusha2%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%
Lusha2%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 four products at 0%, ordered by negative rate
13
Demandbase0%35%49criticized challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
Demandbase0%35%49criticized challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%12
TrustRadius0%14%21accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
TrustRadius0%14%21accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%10
Cognism0%9%22accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%
Cognism0%9%22accepted challenger▼−2Since September 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise. Read over the models both editions asked.2% → 0%11
TechTarget Priority Engine0%6%18accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 0%
TechTarget Priority Engine0%6%18accepted challenger=heldSince September 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise. Read over the models both editions asked.0% → 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
Apollo.io vs ZoomInfoApollo.io vs RB2BApollo.io vs 6senseApollo.io vs G2 Buyer IntentBombora vs DealfrontBombora vs Factors.aiBombora vs ZoomInfoBombora vs RB2BBombora vs 6senseBombora vs G2 Buyer IntentDealfront vs Factors.aiDealfront vs ZoomInfoDealfront vs RB2BDealfront vs 6senseDealfront vs G2 Buyer IntentFactors.ai vs ZoomInfoFactors.ai vs RB2BFactors.ai vs 6senseFactors.ai vs G2 Buyer IntentZoomInfo vs RB2BZoomInfo vs 6senseZoomInfo vs G2 Buyer IntentRB2B vs 6senseRB2B vs G2 Buyer Intent6sense vs G2 Buyer Intent
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 →
01020304050607080910111213Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Apollo.io27%
Apollo.io27%02Bombora27%
Bombora27%03Dealfront12%
Dealfront12%04Factors.ai7%
Factors.ai7%05ZoomInfo7%
ZoomInfo7%06RB2B5%
RB2B5%076sense5%
6sense5%08G2 Buyer Intent2%
G2 Buyer Intent2%09Lusha2%
Lusha2%10Cognism0%
Cognism0%11TechTarget Priority Engine0%
TechTarget Priority Engine0%12TrustRadius0%
TrustRadius0%13Demandbase0%
Demandbase0%What they warned about
Three 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, 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.
6sense41%
26 of 64 labels negative · 11 of 14 models · 5 hard negative
“Just avoid 6sense unless you're at the top of the mid-market range with dedicated RevOps support.” DeepSeek V4 Flash, direct prompt
Bombora27%
18 of 66 labels negative · 10 of 14 models · 3 hard negative
“Bombora ($25K+/year) and 6sense ($60K+/year) are enterprise-level and not suitable for limited budgets” MiniMax M2.5, budget prompt
ZoomInfo36%
18 of 50 labels negative · 10 of 14 models · 3 hard negative
“**Verdict:** Avoid if you need reliable intent signals for SDR outreach. The false positive rate will burn your reps' time and trust.” DeepSeek V4 Flash, negative prompt
Demandbase35%
17 of 49 labels negative · 9 of 14 models · 3 hard negative
“**Avoid** 6sense/Demandbase unless you have the budget ($50K+) and internal resources” Kimi K2, direct 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
75 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. 1065 links across 206 sites, every framing counted. Ranked by the number of answers carrying the site or page. 1 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 · Demandbase57 answers · 87 citations · 14 models
vendor site · RB2B36 answers · 42 citations · 11 models
vendor site · Percepture31 answers · 31 citations · 11 models
vendor site · ZoomInfo30 answers · 56 citations · 10 models
26 answers · 28 citations · 8 models
vendor site · Artisan21 answers · 21 citations · 9 models
vendor site · ZenABM21 answers · 21 citations · 9 models
vendor site · Cognism18 answers · 21 citations · 9 models
vendor site · HG Insights18 answers · 19 citations · 9 models
vendor site · Warmly18 answers · 19 citations · 9 models
vendor site · Salesmotion18 answers · 18 citations · 11 models
vendor site · Prospeo17 answers · 24 citations · 7 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.
51 answers · 13 models
35 answers · 11 models
31 answers · 11 models
21 answers · 9 models
21 answers · 9 models
18 answers · 8 models
17 answers · 8 models
17 answers · 10 models
16 answers · 9 models
15 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 “b2b intent data provider”, “best b2b intent data provider”. 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 | 27% | 1000 | 33,100 | 396 | 111,608 | 94 | ||
| Bombora bombora.com | 27% | 227 | 3,600 | 82 | 17,600 | 4 | 1 | |
| Dealfront leadfeeder.com | 12% | 164 | 590 | 9 | 18,447 | 3 | ||
| Factors.ai factors.ai | 7% | 91 | 590 | 1 | 8,319 | 31 | 8 | |
| ZoomInfo zoominfo.com | 7% | 846 | 135,000 | 1,810 | 6,376,738 | $1,140 | 120 | 2 |
| RB2B rb2b.com | 5% | 95 | 4,400 | 43 | 5,372 | 8 | ||
| 6sense 6sense.com | 5% | 684 | 49,500 | 316 | 108,788 | $1,209 | 120 | 3 |
| Saleshandy saleshandy.com | 4% | 42 | 2,400 | 20 | 193,553 | 2 | ||
| G2 Buyer Intent g2.com | 2% | 163 | 90 | 1 | 2,221,182 | 109 | 7 | |
| Lusha lusha.com | 2% | 322 | 12,100 | 893 | 52,570 | $11 | 57 |
Google's top ten for the two searches hold 12 sites; 3 of them are among the sites the models cited here (cognism.com, demandbase.com, pipeline.zoominfo.com). The first result for “b2b intent data provider” is bombora.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 B2B intent data provider for a mid-market B2B company?”Paraphrase“Which B2B buyer intent data vendor would you recommend to a mid-sized B2B company?”Comparative“What are the top B2B intent data providers and how do they differ?”Budget-constrained“What is the best B2B intent data provider for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a B2B intent data provider. What should we look at?”Negative“Which B2B intent data providers should I avoid or be cautious about?”
Claude Haiku 4.5Bombora, G2 Buyer IntentApollo.io, BomboraChangedno first choiceApollo.iono first choiceagainst: Breeze Prospecting Agent, G2 Buyer Intent, Lead Onion, TrustRadius
Four alternatives
Apollo Intent, Dealfront, Factors.ai, IntentsifyOne alternative
G2 Buyer IntentThree alternatives
Dealfront, Lusha, VisualpingGPT-5.4 miniBomboraBomboraHeldno first choiceDealfrontagainst: 6sense, Bombora, ZoomInfono first choiceagainst: 6sense, Bombora, Demandbase, G2 Buyer Intent, TechTarget Priority Engine, TrustRadius, ZoomInfo
Two alternatives
6sense, G2 Buyer IntentThree alternatives
6sense, Demandbase, ZoomInfoOne alternative
Diginius InsightGemini 3.5 FlashZoomInfoagainst: 6sense, DemandbaseApollo.ioChangedagainst: 6sense, DemandbaseBomboraApollo.io, RB2Bagainst: 6sense, Bombora, DemandbaseBomboraagainst: 6sense, Demandbaseagainst: 6sense, Apollo.io, Demandbase, ZoomInfo
Four alternatives
Bombora, Cognism, Factors.ai, RB2BFour alternatives
Cognism, G2 Buyer Intent, HubSpot Breeze Intelligence, ZoomInfoSix alternatives
6sense, Cognism, Demandbase, G2 Buyer Intent, RB2B, ZoomInfoTwo alternatives
Dealfront, UpLeadSix alternatives
Clay, Common Room, G2 Buyer Intent, Koala, RB2B, TechTarget Priority EnginePerplexity Sonar6senseBomboraChangedagainst: Demandbase, ZoomInfo6sense, Bomboraagainst: Apollo.ioApollo.ioagainst: 6sense, Bombora, Demandbase, ZoomInfono first choicenothing named
Three alternatives
Apollo.io, Dealfront, DemandbaseOne alternative
6senseFive alternatives
Dealfront, Demandbase, G2 Buyer Intent, TechTarget Priority Engine, ZoomInfoThree alternatives
Lead411, Lemlist, RB2BGrok 4.1 FastBomboraagainst: 6senseApollo.io, LushaChangedagainst: 6sense, Bombora, UpLead, ZoomInfo6senseApollo.ioagainst: Bombora, ZoomInfono first choiceagainst: 6sense, Bombora, Demandbase, G2 Buyer Intent, TrustRadius, ZoomInfo
Four alternatives
AdRoll ABM, G2 Buyer Intent, Intentsify, WarmlyFour alternatives
Bombora, Cognism, Demandbase, ZoomInfoFive alternatives
6sense, Dealfront, Factors.ai, Lead Onion, SaleshandyMistral SmallDealfront, Factors.aiWarmlyChangedno first choiceApollo.io, Dealfrontno first choicenothing named
Two alternatives
6sense, LushaThree alternatives
6sense, G2 Buyer Intent, TrustRadiusOne alternative
LushaDeepSeek V4 FlashBomboraagainst: 6senseBomboraHeldagainst: 6sense, Demandbase, ZoomInfono first choiceApollo.io, RB2Bagainst: 6sense, Bombora, Demandbase, ZoomInfono first choiceagainst: 6sense, Bombora, Cognism, Demandbase, SalesIntel, ZoomInfo
Three alternatives
G2 Buyer Intent, Intentsify, ZoomInfoThree alternatives
AdRoll ABM, Apollo.io, G2 Buyer IntentSeven alternatives
6sense, Bombora, Demandbase, G2 Buyer Intent, Intentsify, TechTarget Priority Engine, ZoomInfoThree alternatives
Dealfront, Lusha, SaleshandyLlama 4 Maverickno first choiceApollo.ioChangedno first choiceSaleshandyno first choicenothing named
Two alternatives
Autobound, LushaFour alternatives
Apollo.io, Dealfront, Visualping, WarmlyQwen 3.7 FlashBomboraZoomInfoChangedBomboraApollo.io, Dealfrontagainst: 6sense, Bomborano first choiceagainst: 6sense, Bombora, Cognism, Demandbase, G2 Buyer Intent, HubSpot Breeze Intelligence, RocketReach, ZoomInfo
Four alternatives
6sense, Datanyze, Demandbase, ZoomInfoThree alternatives
6sense, Apollo.io, BomboraThree alternatives
6sense, Cognism, ZoomInfoTwo alternatives
Datanyze, MadKuduKimi K2Dealfront, ZoomInfoagainst: 6sense, Demandbase6sense, BomboraChanged6sense, BomboraApollo.ioagainst: 6sense, Bombora, Demandbaseno first choiceagainst: 6sense, Bombora, ZoomInfo
Two alternatives
Bombora, G2 Buyer IntentThree alternatives
Cognism, Dealfront, ZoomInfo + Intent Add-onTwo alternatives
Demandbase, ZoomInfoThree alternatives
Dealfront, Lead Onion, RB2BSeven alternatives
6sense, Bombora, Cognism, Dealfront, Demandbase, G2 Buyer Intent, ZoomInfoGLM 4.7 FlashXFactors.aiDealfrontChangedBomboraApollo.ioagainst: Hunter, Lushano first choiceagainst: 6sense, Demandbase, ZoomInfo
Three alternatives
Bombora, Dealfront, G2 Buyer IntentTwo alternatives
Apollo.io, Factors.aiFive alternatives
6sense, Apollo.io, Demandbase, G2 Buyer Intent, ZoomInfoFour alternatives
Dealfront, LeadSift, RB2B, SalesmotionMiniMax M2.56senseBombora, ZoomInfoChanged6senseApollo.io, Saleshandyagainst: 6sense, Bomborano first choicenothing named
Seven alternatives
Bombora, Dealfront, Demandbase, G2 Buyer Intent, Prospeo, TrustRadius, ZoomInfo Streaming IntentOne alternative
DemandbaseTwo alternatives
Bombora, DemandbaseThree alternatives
Dealfront, Prospeo, RB2BGPT-6 LunaBomboraBomboraHeldBomboraFactors.aiagainst: G2 Buyer Intentno first choiceagainst: 6sense, Bombora, Demandbase, ZoomInfo
Two alternatives
6sense, G2 Buyer IntentThree alternatives
6sense, Demandbase, G2 Buyer IntentSeven alternatives
6sense, Demandbase, G2 Buyer Intent, Intentsify, TechTarget Priority Engine, TrustRadius, ZoomInfoTwo alternatives
Dealfront, RB2BMuse Glimmer 30BDealfront, Factors.aiagainst: 6sense, Bombora, ZoomInfoBomboraChangedno first choiceApollo.io, RB2Bagainst: 6sense, Bombora, ZoomInfono first choiceagainst: 6sense, Bombora, ZoomInfo, ZoomInfo Streaming Intent
One alternative
WarmlyThree alternatives
6sense, Demandbase, ZoomInfo + Intent Add-onFour alternatives
6sense, Bombora, Demandbase, Informa TechTarget Priority EngineFour alternatives
Dealfront, G2 Buyer Intent, Prospeo, SaleshandyOne alternative
DealfrontBold 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 10:20 | yes | 16 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 09:15 | yes | 4 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:51 | yes | 18 | 26 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-01 08:28 | yes | 21 | 3 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 13:28 | yes | 20 | 9 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:00 | yes | 9 | 4 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 14:15 | yes | 22 | 57 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 12:59 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:10 | no | 0 | 29 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 12:39 | yes | 13 | 30 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 10:28 | yes | 18 | 161 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 09:56 | yes | 8 | 17 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-01 13:33 | yes | 3 | 17 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:19 | yes | 22 | 34 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:14 | yes | 9 | 8 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:45 | yes | 2 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 09:02 | yes | 19 | 27 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-01 12:48 | yes | 19 | 4 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 13:32 | yes | 23 | 9 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:55 | yes | 9 | 6 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 11:27 | yes | 23 | 36 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 13:07 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 09:30 | no | 0 | 35 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 12:09 | yes | 15 | 28 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 11:14 | yes | 13 | 23 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:44 | no | 0 | 42 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-01 13:24 | yes | 3 | 14 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:02 | yes | 18 | 36 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:04 | yes | 17 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:54 | yes | 5 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 08:28 | yes | 20 | 27 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-01 08:04 | yes | 18 | 6 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 14:11 | yes | 16 | 18 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:36 | yes | 9 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 13:25 | yes | 22 | 46 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 11:58 | yes | 5 | 1 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 12:34 | yes | 10 | 31 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 13:41 | yes | 19 | 38 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 12:05 | yes | 20 | 114 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 10:20 | yes | 13 | 17 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:03 | yes | 10 | 43 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 13:30 | yes | 14 | 37 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 08:56 | yes | 15 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 10:09 | yes | 3 | 6 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 13:36 | yes | 26 | 20 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-01 08:24 | yes | 29 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 13:49 | yes | 19 | 9 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 12:18 | yes | 20 | 22 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 08:30 | yes | 21 | 19 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 08:50 | yes | 5 | 1 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 12:25 | no | 0 | 30 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:23 | yes | 16 | 31 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 08:29 | yes | 23 | 56 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 13:26 | yes | 5 | 15 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:41 | yes | 4 | 17 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 09:08 | yes | 11 | 18 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 07:51 | no | 0 | 8 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 11:17 | no | 0 | 10 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 10:59 | yes | 10 | 28 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-01 12:28 | yes | 19 | 4 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 08:07 | yes | 12 | 6 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 07:30 | no | 0 | 8 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 13:54 | yes | 20 | 45 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 13:00 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 13:35 | no | 0 | 38 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 09:27 | yes | 18 | 29 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 07:25 | yes | 16 | 48 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:29 | yes | 5 | 18 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-01 11:39 | yes | 2 | 17 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 08:33 | yes | 13 | 23 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-01 11:23 | yes | 18 | 11 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-01 08:06 | yes | 4 | 9 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-01 11:32 | yes | 28 | 21 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-01 09:48 | yes | 18 | 6 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-01 13:24 | yes | 19 | 12 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-01 11:31 | yes | 5 | 7 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-01 11:31 | yes | 25 | 38 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-01 09:35 | yes | 5 | 1 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-01 12:33 | yes | 18 | 42 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-01 08:59 | yes | 23 | 32 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-01 13:19 | yes | 22 | 28 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-01 11:53 | no | 0 | 10 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-01 12:07 | yes | 5 | 21 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-01 12:16 | yes | 23 | 40 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
5 of 6 flipped
Perplexity Sonar
1 of 4 flipped
Grok 4.1 Fast
4 of 5 flipped
Mistral Small
4 of 4 flipped
DeepSeek V4 Flash
2 of 5 flipped
Llama 4 Maverick
3 of 3 flipped
Qwen 3.7 Flash
4 of 5 flipped
Kimi K2
3 of 4 flipped
GLM 4.7 FlashX
0 of 4 flipped
MiniMax M2.5
3 of 4 flipped
GPT-6 Luna
2 of 4 flipped
Muse Glimmer 30B
4 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
None. Every name in this category resolved on its own.
Unresolved, counted raw
Breeze Prospecting Agent
Buyerfeeds
Customertimes
G2 Signal
Discontinued, still offered
No shut-down product was recommended here.