GPT-6 Astra on iac-bench 2026-10

OpenAI's GPT-6 Astra scored an overall composite of 86.7 (95% CI 86.0–89.8) on the iac-bench 2026-10 evaluation, ranking 3rd of 10 models across 9 attempts on three OpenTofu infrastructure fixtures, with zero failed gates and zero insecure attempts. GPT-6 Astra posted the highest median composite on App Service (95.9) and Cloud SQL (91.3), narrowly ahead of Claude Sonnet 5.5, but fell to the lower half of the field on S3 (72.8) because its bucket module included no retention controls, costing 21 of that fixture's 86 weight points. The 9 attempts cost an estimated $7.26 in total at a list price of $10.00 per million input tokens and $50.00 per million output tokens, evaluated on 2026-10-22 and judged on 2026-10-23.

Upcoming Workshop: Citizen Developer Agentic Software Factory on AWS 11.4.26 @ 12PM PST Register Here https://streamyard.com/watch/umMggUFkVMNu How GPT-6 Astra did on iac-bench 2026-10: an overall composite of 86.7, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules. | Developer | OpenAI | | API identifier | gpt-6-astra | | Access | OpenAI API Responses | | Weights | Closed | | List price USD / M tokens, in / out | 10.00 / 50.00 OpenRouter, 2026-10-23 | | Evaluated | 2026-10-22 generation · 2026-10-23 judge | | Attempts | 9 3 fixtures × 3 samples | | Overall composite | 86.7 95% CI 86.0–89.8 | | Rank | 3 of 10 95% rank interval 1–5 | | Mechanical only / judge only | 83.2 rank 3 / 94.7 rank 2 | | Failed gates · insecure attempts | 0/9 · 0/9 | | Estimated cost, all 9 attempts | $7.26 | GPT-6 Astra has the highest median composite on App Service G003 and on Cloud SQL G002 , where it is narrowly ahead of Claude Sonnet 5.5. It falls into the lower half of the field on S3 G001 . The spread across fixtures is the widest of any model in the top group, and it comes from a single design stance rather than from errors. On S3 it builds a bucket that never deletes anything and offers no retention controls. The rubric treats that as missing data-hygiene items. The judge reads the same module as restrained and free of gold-plating. All 9 attempts planned. No security setting is exposed as an input in any of them. | Fixture | Composite median range | Rubric median | Expertise | Judge median | ✗ gate | ⚠ security | Median inputs | Median output tokens | Median time | Median cost | |---|---|---|---|---|---|---|---|---|---|---| | G001 · S3 | 72.8 72.0–79.6 | 0.640 | 4/7 | 94.7 | 0/3 | 0/3 | 4 | 4,361 | 189 s | $0.318 | | G002 · Cloud SQL | 91.3 89.9–93.9 | 0.908 | 5/9 | 100.0 | 0/3 | 0/3 | 19 | 6,411 | 158 s | $0.447 | | G003 · App Service | 95.9 95.2–98.3 | 1.000 | 4/5 | 89.5 | 0/3 | 0/3 | 19 | 21,718 | 561 s | $1.802 | Rubric items not at full credit, counted over attempts that planned: G001: B1 2/3, H6 3/3, H7 3/3, H9 3/3, H12 3/3, H13 3/3, H14 3/3, H15 2/3; G002: B1 2/3, H4 3/3, H5 3/3, H11 2/3; G003: A7 1/3. Definitions are in Scoring criteria https://www.massdriver.cloud/blogs/iac-bench-2026-10-scoring-criteria . connector enforcement = "REQUIRED" , and validation rejects any attempt to override IAM authentication. On App Service, HTTPS-only and disabled basic-auth publishing are set on both the app and the slot. cloudsql.client and cloudsql.instanceUser with an IAM condition on the instance name, in 3/3 attempts. This closes a cross-instance access path that the rubric does not test excerpt below . S3 has no retention controls 3/3 . It has: H6 ; H7 , so with versioning on, old versions accumulate without limit; H9 , H13 ; force destroy H14 . Together these cost 21 of the fixture's 86 weight points. A code comment gives the reason: the module "cannot know the application's retention requirements." Provider constraints that admit a new major: = 5.0, < 7.0 and = 6.0, < 8.0 in 4 of 9 attempts B1 . Backups and point-in-time recovery cannot be turned off on Cloud SQL H4 / H5 at 0.75 in 3/3 . Duplicate inputs on App Service. Every attempt takes the registry both as a login URL and as an ACR resource ID, though the URL can be looked up from the ID. The judge marked this down under Data sources vs inputs in 8 of 9 readings. optional defaults capacity , staging , registry , checked with preconditions. G002/gpt-6-astra-e3/main.tf lines 102–116 Additive grants, not authoritative policies. Conditions prevent this module's grants from allowing connection/login to other instances in the project. resource "google project iam member" "database access" { for each = local.iam grants project = var.project id member = each.value.member role = each.value.role condition { title = "cloudsql-${var.instance name}" description = "Connection and IAM database login to ${var.instance name} only" expression = "resource.name == 'projects/${var.project id}/instances/${google sql database instance.postgres.name}' && resource.service == 'sqladmin.googleapis.com'" } } Project-level Cloud SQL roles granted with an IAM condition on this one instance. Without the condition, the same grant would allow login to every instance in the project. The S3 fixture shows the largest gap between the two components for this model: mechanical about 64 against a judge grade of 94.7. The doctrine the judge applies does not require retention controls on a general-purpose bucket. The rubric does, because the brief names logs and generated files, data that accumulates. How Claude Fable 5.1 did on iac-bench 2026-10: an overall composite of 86.9, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules. How Claude Haiku 5.5 did on iac-bench 2026-10: an overall composite of 68.0, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules. How Claude Opus 5.5 did on iac-bench 2026-10: an overall composite of 88.9, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules.