Four-Factor Integrity Breakdown & Primary-Source Evidence
Access Model: Strictly Private
"The dataset contains 50 test set scenarios and 50 separate validation scenarios. All model scores reported on this page are based only on the test subset."
"The test and validation sets are separate. Validation results and historical v1 scores are not mixed into this leaderboard."
Originality
Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"The v1.1 workflow definitions contain 6022 workflows across 456 requests in 50 test scenarios. Of these, 1572 (26.1%) check earlier behavior, and 4450 cover the new request. These figures exclude the separate validation set."
Freshness
Weight 20%
10/10
Initial Release: 2026-09Latest Refresh: 2026-11Rolling Updates: No
"In v1.1, we changed iteration prompts to make requirements less ambiguous. We also audited task workflows to check that each assertion follows from the task request. We added a step to the grading process in which a second judge model, Claude Sonnet 5.5, reviews browser-agent failure verdicts against the recorded evidence."
Grading
Weight 15%
7.3/10
Integrity: Independent StandardizedSandbox: live internet
"All models use the same modified OpenHands V1 environment, with terminal access and preconfigured Supabase, Stripe test services, and MailHog. Each task has one ten-hour generation budget shared across its iterations. Evaluation time is excluded."
Frontier Model Standings on Vibe Code Bench 1-100 v1.1
Top 10 active models tracked
Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:
[](https://benchaudit.org/benchmarks/vcb-1-100-v1-1/)