Claude Fable 5.1 on iac-bench 2026-10

Anthropic's Claude Fable 5.1 scored an overall composite of 86.9 (95% CI 83.7–90.2) on iac-bench 2026-10, ranking 2nd of 10 models behind Claude Opus 5.5's 88.9, according to the benchmark's published results. Claude Fable 5.1 planned all 9 modules across 3 fixtures with 0 failed gates and 0 insecure attempts, and its estimated cost for all 9 attempts was $13.97, with a list price of $10.00/$50.00 per million input/output tokens on OpenRouter as of 2026-10-23. The benchmark reported Claude Fable 5.1 was the most expensive model on every fixture, at nearly four times the per-attempt cost of Claude Opus 5.5, and that its interfaces were consistently larger than each audience's input budget.

November changelog: Runtimes & OIDC cloud credentials, plus imports with Claude Code & opencode Read more https://www.massdriver.cloud/blogs/november-2026-changelog 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. All ten models side by side, with a sortable leaderboard, picks by use case and the cost of each: LLM rankings https://www.massdriver.cloud/llm-rankings . | Developer | Anthropic | | API identifier | claude-fable-5-1 | | Access | Anthropic API | | 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 | 86.9 95% CI 83.7–90.2 | | Rank | 2 of 10 95% rank interval 1–5 | | Mechanical only / judge only | 85.0 rank 2 / 91.2 rank 5 | | Failed gates · insecure attempts | 0/9 · 0/9 | | Estimated cost, all 9 attempts | $13.97 | Claude Fable 5.1 places second, close behind Claude Opus 5.5. All 9 modules planned, and none had a security finding. Together with Claude Opus 5.5, it shows the deepest service expertise in the field on Cloud SQL and App Service median 8/9 and 5/5 expertise items . Its cost is the main counterweight: it was the most expensive model on every fixture, at nearly four times the per-attempt cost of Claude Opus 5.5. Its interfaces are also consistently larger than the benchmark's budget for each audience. | Fixture | Composite median range | Rubric median | Expertise | Judge median | ✗ gate | ⚠ security | Median inputs | Median output tokens | Median time | Median cost | |---|---|---|---|---|---|---|---|---|---|---| | G001 · S3 | 85.6 82.6–90.2 | 0.826 | 6/7 | 92.1 | 0/3 | 0/3 | 12 | 12,112 | 302 s | $0.935 | | G002 · Cloud SQL | 85.6 79.0–90.0 | 0.832 | 8/9 | 94.7 | 0/3 | 0/3 | 30 | 14,402 | 196 s | $1.229 | | G003 · App Service | 89.5 88.5–94.9 | 0.911 | 5/5 | 86.8 | 0/3 | 0/3 | 28 | 27,308 | 566 s | $2.157 | Rubric items not at full credit, counted over attempts that planned: G001: A5 3/3, B1 3/3, H12 2/3, H13 3/3, H15 1/3; G002: A8 3/3, B1 3/3, H4 3/3, H5 3/3, H10 1/3, H11 3/3; G003: A7 3/3. Definitions are in Scoring criteria https://www.massdriver.cloud/blogs/iac-bench-2026-10-scoring-criteria . environment input sets the network apps-<env , the HA type and backup retention. terraform data guard on App Service that holds five capacity rules. A5 , 11–13 inputs against 8. A8 , 26–37 inputs against 25. One attempt scored zero. A7 , 27–29 inputs against 20. intelligent tiering after days . = , or = 5.30, < 7.0 , in 6 of 9 attempts B1 . H11 lost in 3/3 . One attempt adds a deletion policy input, but its default is DELETE . One attempt also writes a break-glass password into state H10 . H13 , 3/3 . observability.tf , scaling.tf , slot.tf , but still lets main.tf grow past 200 lines in 4/9 attempts. for each for multiplicity and count only as a switch. G002/claude-fable-5-1-e1/main.tf lines 11–21 Flags that are the same on every instance and cannot be overridden by callers. enforced database flags = { "cloudsql.iam authentication" = "on" "log connections" = "on" "log disconnections" = "on" "log checkpoints" = "on" "log lock waits" = "on" "log temp files" = "0" } database flags = merge var.database flags, local.enforced database flags The same pattern as the leader, with a broader enforced audit set: connections, disconnections, checkpoints, lock waits and temporary files are always logged. 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. How Claude Sonnet 5.5 did on iac-bench 2026-10: an overall composite of 86.1, scores per fixture, strengths, weaknesses and the patterns in its OpenTofu modules.