{"slug": "claude-opus-5-5-on-iac-bench-2026-10", "title": "Claude Opus 5.5 on iac-bench 2026-10", "summary": "Anthropic's Claude Opus 5.5 scored an overall composite of 88.9 (95% CI 87.5–91.5) on the iac-bench 2026-10 infrastructure-as-code benchmark, ranking 2nd of 16 models behind Claude Fable 5.2, according to Massdriver's LLM rankings. Across 9 attempts on 3 fixtures (S3, Cloud SQL, App Service), Claude Opus 5.5 failed 0 mandatory security gates and produced 0 insecure attempts, with a worst attempt of 85.0 and an estimated total cost of $3.58 at list prices of $4.00/$20.00 per million input/output tokens. Its lead over GPT-6.1 Sol, Claude Fable 5.1 and GPT-6 Astra fell within the three-sample margin (bootstrap win probabilities 0.74, 0.84 and 0.86), while its modules hard-coded security settings and merged enforced database flags last so inputs could not disable them.", "body_md": "New: LLM Rankings are live!\n\n[See how the top LLMs rank on real infrastructure tasks](https://www.massdriver.cloud/llm-rankings)\n\nHow 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.\n\nEvery model evaluated on the 2026-10 fixtures side by side, with a sortable leaderboard, picks by use case and the cost of each: [LLM rankings](https://www.massdriver.cloud/llm-rankings).\n\n| Developer | Anthropic | \n| API identifier | `claude-opus-5-5` | \n| Access | Anthropic API | \n| Weights | Closed | \n| List price (USD / M tokens, in / out) | 4.00 / 20.00 (OpenRouter, 2026-10-23) | \n| Evaluated | 2026-10-22 (generation) · 2026-10-23 (judge) | \n| Attempts | 9 (3 fixtures × 3 samples) | \n| **Overall composite** | **88.9** (95% CI 87.5–91.5) | \n| Rank | 2 of 16 (95% rank interval 2–5) | \n| Mechanical only / judge only | 86.4 (rank 2) / 94.7 (rank 2) | \n| Failed gates · insecure attempts | 0/9 · 0/9 | \n| Estimated cost, all 9 attempts | $3.58 | \n\nClaude Opus 5.5 has the second-highest overall score in the 2026-10 release, behind Claude Fable 5.2. It is the only model besides Claude Fable 5.2 whose 95% rank interval stays within the top five. All 9 of its modules planned, and none failed a mandatory security item. Its weakest attempt (85.0) is the strongest worst case in the release after Claude Fable 5.2's (88.6). Its overall lead over GPT-6.1 Sol, Claude Fable 5.1 and GPT-6 Astra is within the margin of three samples (bootstrap win probabilities 0.74, 0.84 and 0.86). The clearer distinction is consistency: no fixture produced a weak attempt.\n\nIts modules fix the security settings in code and do not offer them as inputs. They derive values from a small set of concept inputs, and they include most of the service-specific practices the benchmark checks for: 7/7 on S3, 8/9 on Cloud SQL and 5/5 on App Service, in every sample.\n\n| Fixture | Composite median (range) | Rubric median | Expertise | Judge median | ✗ gate | ⚠ security | Median inputs | Median output tokens | Median time | Median cost | \n|---|---|---|---|---|---|---|---|---|---|---|\n| G001 · S3 | 87.9 (87.9–90.2) | 0.826 | 7/7 | 97.4 | 0/3 | 0/3 | 10 | 11,128 | 243 s | $0.328 | \n| G002 · Cloud SQL | 88.6 (85.0–93.5) | 0.832 | 8/9 | 100.0 | 0/3 | 0/3 | 29 | 8,733 | 112 s | $0.245 | \n| G003 · App Service | 90.2 (89.5–93.2) | 0.911 | 5/5 | 86.8 | 0/3 | 0/3 | 28 | 21,622 | 468 s | $0.635 | \n\nRubric items not at full credit, counted over attempts that planned: G001: `A5` 3/3, `B1` 3/3, `H9` 2/3, `H13` 3/3; G002: `A8` 3/3, `B1` 2/3, `H3` 1/3, `H4` 3/3, `H5` 3/3, `H11` 3/3; G003: `A7` 3/3. Definitions are in [Scoring criteria](https://www.massdriver.cloud/blogs/iac-bench-2026-10-scoring-criteria).\n\n`ipv4_enabled = false` and `ssl_mode = \"ENCRYPTED_ONLY\"` are literals.`database_flags` input. The module merges its own required flags (IAM authentication,\npgaudit, connection logging) last, so no input can turn them off (excerpt below).`force_destroy` is refused in\nproduction, and on Cloud SQL the Enterprise Plus log retention is checked against the\nedition.`A8` is lost in 3/3.`A7` is lost in 3/3.`deletion_policy` (`H11` lost in\n3/3).`H4` and `H5` earn\npartial credit.`H3`).` H13`, 3/3), and two of three offer no access logging at all (` H9`).`>= 5.0, < 7.0`, or unbounded `>= 5.0`,\nin 5/9 attempts (`B1`).` ignore_changes = [worker_count]`;` environment` (`apps-${var.environment}`), and so does high availability.` main.tf` by default.\n`G002/claude-opus-5-5-e3/main.tf` lines 7–17\n\n```\n  # Settings that must be identical on every instance. These win over\n  # anything supplied in var.database_flags.\n  enforced_flags = {\n    \"cloudsql.iam_authentication\" = \"on\"\n    \"cloudsql.enable_pgaudit\"     = \"on\"\n    \"pgaudit.log\"                 = var.pgaudit_log_classes\n    \"log_connections\"             = \"on\"\n    \"log_disconnections\"          = \"on\"\n  }\n\n  database_flags = merge(var.database_flags, local.enforced_flags)\n```\n\nThe DBA team keeps an open-ended flags input, but the module's own flags are merged last, so no input can switch off IAM authentication or connection auditing.\n\nThe judge is Claude Opus 5.5, so this page grades the judge's own model. Its grades for\nthis model are 97.4 (S3) and 100 (Cloud SQL). Without the judge, ranking on the mechanical\nscore alone, Claude Opus 5.5 still ranks second (86.4), behind Claude Fable 5.2, so the top\nof the ranking does not depend on the judge. See [Methodology §5.3](https://www.massdriver.cloud/blogs/iac-bench-2026-10-methodology#53-known-judge-risks).\n\nHow 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.\n\nHow Claude Fable 5.2 did on iac-bench 2026-10: an overall composite of 93.9, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules.\n\nHow 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.", "url": "https://wpnews.pro/news/claude-opus-5-5-on-iac-bench-2026-10", "canonical_source": "https://www.massdriver.cloud/blogs/iac-bench-2026-10-claude-opus-5-5", "published_at": "2026-11-04 00:00:00+00:00", "updated_at": "2026-11-21 01:13:20.552677+00:00", "lang": "en", "topics": ["ai-research", "large-language-models", "ai-tools", "developer-tools"], "entities": ["Anthropic", "Claude Opus 5.5", "Claude Fable 5.2", "GPT-6.1 Sol", "GPT-6 Astra", "Massdriver", "iac-bench", "OpenTofu"], "also_reported_by": [], "takeaway": "Claude Opus 5.5 scored 88.9 overall (95% CI 87.5–91.5) with 0/9 failed gates and 0/9 insecure attempts, and its modules merged enforced database flags last so no input could disable IAM authentication, pgaudit or connection logging.", "recommendation": {"advice": "Evaluate IaC-generating models on multiple fixtures with 3 samples each and report confidence intervals; Claude Opus 5.5's 88.9 composite carried a 95% CI of 87.5–91.5, so single-run rankings can mislead.", "playbook": "evals-testing", "playbook_url": "https://wpnews.pro/playbooks/evals-testing"}, "alternates": {"html": "https://wpnews.pro/news/claude-opus-5-5-on-iac-bench-2026-10", "markdown": "https://wpnews.pro/news/claude-opus-5-5-on-iac-bench-2026-10.md", "text": "https://wpnews.pro/news/claude-opus-5-5-on-iac-bench-2026-10.txt", "jsonld": "https://wpnews.pro/news/claude-opus-5-5-on-iac-bench-2026-10.jsonld"}}