Workflow orchestration
Asked as “workflow orchestration tool”, and as “data pipeline orchestrator”, on behalf of a mid-market B2B company. 53 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each.
Standing · first-choice share
25%
Contested · Dagster 15%
25Prefect15Dagster13Apache Airflow47others
25% of first choices, contested.
Since October 2026▲+4Since October 2026: 21% → 25%, +4 points. Inside the 11-point floor: within noise.Prefect held the lead, +4 points on 21%, 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
Make33%Contested▲+9Since October 2026: 24% → 33%, +9 points. Inside the 11-point floor: within noise.Standing →Mid-market
Prefect25%Contested▲+4Since October 2026: 21% → 25%, +4 points. Inside the 11-point floor: within noise.This pageEnterprise
Apache Airflow29%Contested▲+3Since October 2026: 26% → 29%, +3 points. Inside the 11-point floor: within noise.Standing →
Make33%Contested▲+9Since October 2026: 24% → 33%, +9 points. Inside the 11-point floor: within noise.Standing →Mid-marketPrefect25%Contested▲+4Since October 2026: 21% → 25%, +4 points. Inside the 11-point floor: within noise.This pageEnterpriseApache Airflow29%Contested▲+3Since October 2026: 26% → 29%, +3 points. Inside the 11-point floor: within noise.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 October 2026
01Prefect25%2%58accepted challenger▲+4Since October 2026: 21% → 25%, +4 points. Inside the 11-point floor: within noise.21% → 25%
Prefect25%2%58accepted challenger▲+4Since October 2026: 21% → 25%, +4 points. Inside the 11-point floor: within noise.21% → 25%02
Dagster15%4%50accepted challenger▲+1Since October 2026: 14% → 15%, +1 point. Inside the 11-point floor: within noise.14% → 15%
Dagster15%4%50accepted challenger▲+1Since October 2026: 14% → 15%, +1 point. Inside the 11-point floor: within noise.14% → 15%03Apache Airflow13%32%69criticized challenger▼−4Since October 2026: 17% → 13%, −4 points. Inside the 11-point floor: within noise.17% → 13%
Apache Airflow13%32%69criticized challenger▼−4Since October 2026: 17% → 13%, −4 points. Inside the 11-point floor: within noise.17% → 13%04
n8n13%3%32accepted challenger▼−1Since October 2026: 14% → 13%, −1 point. Inside the 11-point floor: within noise.14% → 13%
n8n13%3%32accepted challenger▼−1Since October 2026: 14% → 13%, −1 point. Inside the 11-point floor: within noise.14% → 13%05Make9%10%29accepted challenger▼−3Since October 2026: 12% → 9%, −3 points. Inside the 11-point floor: within noise.12% → 9%
Make9%10%29accepted challenger▼−3Since October 2026: 12% → 9%, −3 points. Inside the 11-point floor: within noise.12% → 9%06
Workato8%25%20criticized challenger▲+3Since October 2026: 5% → 8%, +3 points. Inside the 11-point floor: within noise.5% → 8%
Workato8%25%20criticized challenger▲+3Since October 2026: 5% → 8%, +3 points. Inside the 11-point floor: within noise.5% → 8%07
Zapier6%32%31criticized challenger▲+3Since October 2026: 3% → 6%, +3 points. Inside the 11-point floor: within noise.3% → 6%
Zapier6%32%31criticized challenger▲+3Since October 2026: 3% → 6%, +3 points. Inside the 11-point floor: within noise.3% → 6%08
Temporal4%12%42accepted challenger▲+2Since October 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise.2% → 4%
Temporal4%12%42accepted challenger▲+2Since October 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise.2% → 4%09Camunda Platform 82%11%27accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%
10
Microsoft Power Automate2%14%22accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise.2% → 2%
Microsoft Power Automate2%14%22accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise.2% → 2%Show the six products at 0%, ordered by negative rate
16Luigi0%92%12criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
15
AWS Step Functions0%25%20criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
AWS Step Functions0%25%20criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%12
Argo Workflows0%17%23accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Argo Workflows0%17%23accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%13
Astronomer Astro0%14%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Astronomer Astro0%14%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%14
Amazon Managed Workflows for Apache Airflow0%10%10accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Amazon Managed Workflows for Apache Airflow0%10%10accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%11
Kestra0%9%22accepted challenger▼−3Since October 2026: 3% → 0%, −3 points. Inside the 11-point floor: within noise.3% → 0%
Kestra0%9%22accepted challenger▼−3Since October 2026: 3% → 0%, −3 points. Inside the 11-point floor: within noise.3% → 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 can't be told apart from repeat variation, and both are shown. Each index measures its own floor from its own repeat, over its own categories, so the floor differs from one index to the next. Both editions asked the same fourteen models. 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
Prefect vs MakePrefect vs WorkatoPrefect vs ZapierPrefect vs TemporalDagster vs Apache AirflowDagster vs n8nDagster vs MakeDagster vs WorkatoDagster vs ZapierDagster vs TemporalApache Airflow vs n8nApache Airflow vs MakeApache Airflow vs WorkatoApache Airflow vs ZapierApache Airflow vs Temporaln8n vs Maken8n vs Workaton8n vs Zapiern8n vs TemporalMake vs WorkatoMake vs ZapierMake vs TemporalWorkato vs ZapierWorkato vs TemporalZapier vs Temporal
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 →
0102030405060708C09
101112131415L16
Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative40%
Key
01Prefect25%
Prefect25%02Dagster15%
Dagster15%03Apache Airflow13%
Apache Airflow13%04n8n13%
n8n13%05Make9%
Make9%06Workato8%
Workato8%07Zapier6%
Zapier6%08Temporal4%
Temporal4%09Camunda Platform 82%
10Microsoft Power Automate2%
Microsoft Power Automate2%11Kestra0%
Kestra0%12Argo Workflows0%
Argo Workflows0%13Astronomer Astro0%
Astronomer Astro0%14Amazon Managed Workflows for Apache Airflow0%
Amazon Managed Workflows for Apache Airflow0%15AWS Step Functions0%
AWS Step Functions0%16Luigi0%
What they warned about
One of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Perplexity Sonar, Grok 4.20, Mistral Small, DeepSeek V4 Flash, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX, MiniMax M2.5, GPT-6 Luna 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.
Apache Airflow32%
22 of 69 labels negative · 12 of 14 models
“running Airflow in production requires managing the scheduler, workers, metadata database, and web server, and it's not suited for business process automation or teams without Python expertise” Claude Haiku 4.5, budget prompt
Luigi
92%
11 of 12 labels negative · 9 of 14 models · 7 hard negative
“Why to avoid: ... It lacks dynamic DAG generation during runtime, has a very basic UI” Gemini 3.5 Flash, negative prompt
Zapier32%
10 of 31 labels negative · 8 of 14 models · 1 hard negative
“Avoid or be cautious with Zapier, Make, and Workato for anything beyond simple automation due to cost and scalability issues.” Mistral Small, negative prompt
Azkaban
100%
5 of 5 labels negative · 5 of 14 models · 3 hard negative
“Why to avoid: Built by LinkedIn a decade ago... has a very small active open-source community today.” Gemini 3.5 Flash, negative prompt
What they cite
Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted.
Sites the answers cite
71 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. 805 links across 270 sites, every framing counted. Ranked by the number of answers carrying the site or page. 31 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 · Zapier24 answers · 32 citations · 9 models
vendor site · ONES.com22 answers · 38 citations · 10 models
vendor site · Kestra21 answers · 40 citations · 8 models
19 answers · 34 citations · 10 models
vendor site · GitHub19 answers · 30 citations · 8 models
16 answers · 17 citations · 8 models
15 answers · 15 citations · 8 models
vendor site · Prefect12 answers · 15 citations · 6 models
12 answers · 12 citations · 7 models
vendor site · LarkSuite11 answers · 12 citations · 8 models
vendor site · Skyvia11 answers · 12 citations · 8 models
11 answers · 11 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.
23 answers · 9 models
15 answers · 8 models
12 answers · 6 models
12 answers · 7 models
11 answers · 6 models
11 answers · 6 models
10 answers · 6 models
9 answers · 7 models
9 answers · 6 models
9 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 “best workflow orchestration tool”, “workflow orchestration tool”, “workflow orchestration 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 |
|---|---|---|---|---|---|---|---|
| Prefect prefect.io | 25% | 140 | 14,800 | 1,159 | 8,198 | $691 | 6 |
| Dagster dagster.io | 15% | 121 | 5,400 | 143 | 23,407 | 34 | |
| Apache Airflow apache.org | 13% | 202 | 8,100 | 271 | 1,144,025 | 0 | |
| n8n n8n.io | 13% | 111 | 165,000 | 2,786 | 133,599 | 42 | |
| Make make.com | 9% | 127 | 135,000 | 12,939,045 | 439,031 | 76 | |
| Workato workato.com | 8% | 80 | 14,800 | 405 | 38,042 | $20 | 120 |
| Zapier zapier.com Zapier 6%, Zapier/Make 2% | 8% | 172 | 165,000 | 2,145 | 7,333,309 | $230 | 120 |
| Temporal temporal.io | 4% | 93 | 49,500 | 13,896 | 41,181 | 70 | |
| Camunda Platform 8 camunda.com | 2% | 81 | 13,960 | 35 | |||
| Microsoft parent site Microsoft Power Automate 2% | 2% | 323 | 2,240,000 | 403,136 |
Google's top ten for the three searches hold 17 sites; 2 of them are among the sites the models cited here (github.com, thedigitalprojectmanager.com). The first result for “best workflow orchestration tool” is guptadeepak.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 workflow orchestration tool for a mid-market B2B company?”Paraphrase“Which data pipeline orchestrator would you recommend to a mid-sized B2B company?”Comparative“What are the top workflow orchestration tools and how do they differ?”Budget-constrained“What is the best workflow orchestration tool for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating a workflow orchestration tool. What should we look at?”Negative“Which workflow orchestration tools should I avoid or be cautious about?”
Claude Haiku 4.5Prefect, Zapier/MakePrefectChangedagainst: Apache AirflowApache AirflowMake, n8nagainst: Apache Airflowno first choiceagainst: Apache Airflow, Azkaban, Dagster, Luigi, Prefect, Zapier
One alternative
Apache AirflowOne alternative
DagsterFive alternatives
Camunda Platform 8, Dagster, Kestra, Prefect, TemporalTwo alternatives
Argo Workflows, Conductor OSSGPT-5.4 miniTemporalApache AirflowChangedApache Airflowagainst: LuigiApache Airflow, Prefectno first choiceagainst: Apache Airflow, Argo Workflows, Luigi
Two alternatives
Apache Airflow, PrefectTwo alternatives
Dagster, PrefectSix alternatives
AWS Step Functions, Argo Workflows, Dagster, Flyte, Prefect, TemporalGemini 3.5 FlashDagster, Prefect, Temporal, n8nagainst: Apache Airflow, Workato, ZapierDagsterChangedagainst: Apache AirflowApache AirflowPrefectagainst: Amazon Managed Workflows for Apache Airflow, Apache Airflow, Astronomer Astrono first choiceagainst: AWS Step Functions, Apache Airflow, Apache Oozie, Argo Workflows, Azkaban, Luigi
Three alternatives
Amazon Managed Workflows for Apache Airflow, Astronomer Astro, MakeOne alternative
PrefectFive alternatives
Argo Workflows, Dagster, Kestra, Prefect, TemporalFour alternatives
Dagster, Kestra, Temporal, n8nFour alternatives
AWS Step Functions, Dagster, Prefect, TemporalPerplexity SonarWorkatoagainst: LeanDataDagsterChangedno first choiceMakeagainst: Apache Airflow, Camunda Platform 8, ServiceNow Workflow, Workatono first choiceagainst: AWS Step Functions, Apache Airflow, Azure Logic Apps, Camunda Platform 8, Inngest, Make, Microsoft Power Automate, Zapier, n8n
Four alternatives
Make, Microsoft Power Automate, Zapier, n8nTwo alternatives
Apache Airflow, KestraTwelve alternatives
Apache Airflow, Argo Workflows, Camunda Platform 8, Dagster, Kestra, Make, Microsoft Power Automate, Prefect, Temporal, Workato, Zapier, n8nTwo alternatives
Microsoft Power Automate, n8nGrok 4.20Zapieragainst: IBM, IFTTT, OraclePrefectChangedagainst: Apache Airflow, Kubeflow, Luigi, Mageno first choiceApache AirflowApache Airflow, Prefectagainst: AWS Step Functions, Activiti, Apache Airflow, Azure Data Factory, Camunda Platform 8, Google Cloud Workflows, Kestra, Luigi, Make, Oozie, Temporal, Workato, Zapier
Six alternatives
Camunda Platform 8, Make, Microsoft Power Automate, SnapLogic, Workato, n8nTwo alternatives
Astronomer Astro, DagsterFive alternatives
Apache Airflow, Argo Workflows, Dagster, Prefect, TemporalSix alternatives
Argo Workflows, Camunda Platform 8, Dagu, Prefect, Temporal, n8nThree alternatives
Camunda Platform 8, Dagster, TemporalMistral SmallPrefectDagster, PrefectChangedApache Airflow, PrefectZapier, n8nno first choiceagainst: Apache Airflow, Make, Microsoft Power Automate, UiPath, Workato, Zapier
Five alternatives
Apache Airflow, Camunda Platform 8, Dagster, Microsoft Power Automate, WorkatoThree alternatives
Apache Airflow, Kestra, Microsoft Fabric Data FactorySix alternatives
Dagster, IBM watsonx Orchestrate, Kubeflow, LangChain, Metaflow, WorkatoThree alternatives
Make, ONES.com, TemporalDeepSeek V4 FlashWorkatoDagsterChangedagainst: Apache AirflowApache Airflown8nno first choiceagainst: Apache Airflow, Appian, Microsoft Power Automate, Pegaagainst: Airbyte, Apache Airflow, Argo Workflows, Luigi, Orchest, laravel-workflow
Four alternatives
Make, Prefect, Zapier, n8nOne alternative
PrefectSix alternatives
AWS Step Functions, Argo Workflows, Dagster, Kestra, Prefect, TemporalTwo alternatives
Apache Airflow, MakeLlama 4 MaverickPrefectPrefectHeldno first choiceONES.comno first choiceagainst: Apache Airflow, Temporal, Zapier
Seven alternatives
Apache Airflow, Dagster, Make, Microsoft Power Automate, Workato, Zapier, n8nTwo alternatives
Apache Airflow, DagsterFour alternatives
Make, UiPath, Zapier, n8nQwen 3.7 FlashMakeagainst: ZapierDagsterChangedagainst: Apache AirflowApache Airflowagainst: Netflix ConductorMakeagainst: Zapierno first choiceagainst: Node-RED, Oracle, SAP, Temporal, Zapieragainst: AWS Step Functions, Apache Airflow, Apache Kafka Connect, Apache Oozie, Atlassian Bamboo, Custom Bash Scripts / Crontabs, Docker Swarm, Jenkins, Luigi, Mesos/Marathon, Yahoo! Azkaban
Three alternatives
Apache Airflow, Microsoft Power Automate, n8nFour alternatives
Astronomer Astro, Google Cloud Composer, Mage, PrefectSix alternatives
AWS Step Functions, Argo Workflows, Camunda Platform 8, Dagster, Prefect, TemporalTwo alternatives
Apache Airflow, n8nSeven alternatives
Boomi, Camunda Platform 8, Cflow, Nintex, Relay.app, Tray.io, WorkatoKimi K2Microsoft Power Automate, ZapierDagsterChangedagainst: Apache Airflow via AstronomerApache AirflowApache Airflowagainst: Astronomer Astro, TemporalCamunda Platform 8against: Apache Airflow, Apache NiFi, Apache Oozie, Azkaban, Flo, Luigi
Three alternatives
Make, Workato, n8nOne alternative
PrefectFive alternatives
Argo Workflows, Dagster, Kestra, Prefect, TemporalFour alternatives
Dagster, Dagu, Kestra, PrefectFour alternatives
Apache Airflow, Microsoft Power Automate, Temporal, n8nGLM 4.7 FlashXMakeApache AirflowChangedagainst: DataChannel, KeboolaApache Airflown8nno first choiceagainst: Boomi, MuleSoft Anypoint Platform, Workato, Zapieragainst: Activiti, Apache ODE, Apache OFBiz Workflow, Azkaban, Cadence, Luigi, Maestro, OpenWFE, Orchest, dsh-agent-orchestrator, laravel-workflow/laravel-workflow
Five alternatives
Microsoft Power Automate, Tray.io, Workato, Zapier, n8nFive alternatives
Amazon Managed Workflows for Apache Airflow, Astronomer Astro, Dagster, Google Cloud Composer, PrefectSeven alternatives
Argo Workflows, Dagster, Flyte, Kestra, Mage, Prefect, TemporalFour alternatives
Apache Airflow, Microsoft Power Automate, Temporal, ZapierSeven alternatives
Apache Airflow, Camunda Platform 8, Make, Prefect, Temporal, Tray.io, n8nMiniMax M2.5no first choicePrefectChangedApache AirflowPrefectno first choiceagainst: Apache Oozie, Azkaban, Luigi
Five alternatives
AWS Glue, AWS Step Functions, Apache Airflow, Azure Data Factory, DagsterFour alternatives
Argo Workflows, Dagster, Prefect, TemporalTwo alternatives
Apache Airflow, DagsterGPT-6 LunaWorkatoDagsterChangedno first choicen8nno first choiceagainst: AWS Step Functions, Apache Airflow, Argo Workflows, Temporal
Four alternatives
Camunda Platform 8, Microsoft Power Automate, Temporal, n8nTwo alternatives
Apache Airflow, PrefectTwo alternatives
Apache Airflow, PrefectMuse Glimmer 30BWorkatoApache AirflowChangedApache Airflown8nno first choiceagainst: Apache Airflow, Appian, Dagster, Kestra, Pega, ServiceNow Workflow
Five alternatives
Boomi, Make, Microsoft Power Automate, SnapLogic, ZapierFour alternatives
Amazon Managed Workflows for Apache Airflow, Astronomer Astro, Dagster, PrefectFive alternatives
Argo Workflows, Dagster, Kestra, Prefect, TemporalTwo alternatives
Apache Airflow, PrefectBold 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.
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 | 2026-11-01 11:46 | no | 0 | 5 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 08:47 | yes | 3 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 17:29 | no | 0 | 18 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 11:43 | yes | 10 | 5 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 15:47 | yes | 5 | 12 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 16:34 | yes | 5 | 7 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:09 | yes | 19 | 19 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 15:02 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 12:41 | yes | 5 | 27 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 09:28 | yes | 20 | 23 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:30 | yes | 24 | 71 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 12:49 | no | 0 | 77 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 16:25 | yes | 5 | 13 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 17:18 | yes | 13 | 17 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:38 | yes | 18 | 11 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 14:23 | yes | 2 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 12:48 | no | 0 | 15 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 11:19 | yes | 10 | 4 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:38 | yes | 5 | 13 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:26 | yes | 5 | 6 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 13:25 | yes | 19 | 29 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 17:51 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 17:28 | yes | 5 | 27 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:01 | yes | 19 | 24 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 08:59 | yes | 13 | 20 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:57 | yes | 5 | 65 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 10:39 | yes | 3 | 11 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:07 | yes | 15 | 22 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 14:30 | yes | 16 | 14 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 19:17 | yes | 3 | 8 s |
| Comparative | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 11:06 | yes | 8 | 24 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 12:34 | yes | 10 | 7 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 17:47 | yes | 10 | 14 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 13:16 | yes | 5 | 8 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 17:35 | yes | 20 | 42 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:15 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 18:22 | yes | 5 | 30 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 13:12 | yes | 14 | 32 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 14:42 | yes | 15 | 296 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 14:03 | yes | 25 | 89 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 14:09 | yes | 7 | 22 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 10:59 | yes | 15 | 24 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 15:48 | yes | 17 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:10 | no | 0 | 3 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 12:40 | no | 0 | 16 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 09:36 | yes | 10 | 3 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:16 | yes | 5 | 10 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 13:05 | yes | 5 | 6 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:19 | yes | 19 | 18 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 10:39 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:53 | yes | 10 | 31 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 13:24 | yes | 10 | 43 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:35 | yes | 20 | 24 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 16:39 | yes | 5 | 22 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 16:26 | yes | 3 | 11 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 11:47 | yes | 15 | 25 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:19 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:10 | no | 0 | 7 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:21 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 17:04 | yes | 10 | 7 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:57 | yes | 5 | 13 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 18:15 | no | 0 | 8 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:43 | yes | 22 | 53 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 13:13 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:42 | yes | 9 | 42 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 16:50 | yes | 23 | 36 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 17:43 | yes | 25 | 169 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:27 | no | 0 | 16 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 18:58 | yes | 2 | 15 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 15:29 | yes | 14 | 20 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:41 | yes | 18 | 11 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 13:19 | yes | 4 | 6 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:24 | no | 0 | 16 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 13:13 | yes | 10 | 4 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:45 | yes | 10 | 13 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:00 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 18:21 | yes | 24 | 33 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:15 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 14:49 | no | 0 | 32 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 15:10 | yes | 25 | 47 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 14:08 | yes | 24 | 25 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:34 | yes | 19 | 84 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 19:15 | yes | 4 | 13 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 14:04 | yes | 22 | 25 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
Astronomer read as Astronomer Astro
Camunda read as Camunda Platform 8
Camunda Platform read as Camunda Platform 8
Databricks read as Databricks Lakeflow Jobs
MuleSoft read as MuleSoft Anypoint Platform
ServiceNow read as ServiceNow Workflow
Unresolved, counted raw
Apache Airflow via Astronomer
Apache DolphinScheduler
Apache Kafka Connect
Apache ODE
Apache OFBiz Workflow
Conductor OSS
ControlHub
Custom Bash Scripts / Crontabs
DeepSeek Harness
Flo
LeanData
Mesos/Marathon
OpenWFE
Orby AI
Relay.app
ServiceNow Flow Designer
Timeplus
Yahoo! Azkaban
dsh-agent-orchestrator
laravel-workflow
laravel-workflow/laravel-workflow
Discontinued, still offered
No shut-down product was recommended here.