Eleven of fourteen models named Terraform first on the direct prompt; four named OpenTofu. Both were named by all fourteen models and Terraform carries 85 labels and OpenTofu 54, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
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; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the infrastructure as code page.
Across every category in the October 2026 Edition, Terraform and OpenTofu were named in the same answer 156 times, of the 232 answers naming Terraform and the 159 naming OpenTofu. In those answers OpenTofu took the first choice forty-one times and Terraform fifty-seven.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Multi-cloud IaC | OpenTofu (not Terraform)” Kimi K2 · negative prompt · hard negative
“Unlike Terraform's HCP Terraform (which has a free tier limited to 500 managed resources and charges ~$0.10/resource/month beyond that)” Grok 4.20 · budget prompt · soft negative
“be cautious if you need a fully permissive open-source stack or want to minimize licensing risk. HashiCorp moved Terraform to BUSL” GPT-5.4 mini · negative prompt · soft negative
“Terraform remains the default for multi‑cloud ops teams, with the deepest tooling and IBM backing, but the BSL license restricts commercial productization.” GLM 4.7 FlashX · comparative prompt · first choice
“*Look at:* HashiCorp Terraform. It is the resume-standard skill... the ecosystem (modules, providers, integrations) is unmatched.” Qwen 3.7 Flash · scale prompt · first choice
“the most common, low risk choice today is Terraform / OpenTofu for multi-cloud provisioning, with a remote state backend” Muse Glimmer 30B · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“Use OpenTofu as your primary provisioning tool — it's free, open source, and fully compatible with the massive Terraform ecosystem.” DeepSeek V4 Flash · budget prompt · first choice
“write your code in standard HCL (which is fully compatible with both OpenTofu and Terraform). This keeps your options open.” Gemini 3.5 Flash · scale prompt · first choice
“I'd recommend starting with OpenTofu (or Terraform if you prefer HashiCorp's support and don't mind the BSL license)” DeepSeek V4 Flash · paraphrase prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.