Vibe Code Bench
As of Nov 3, 2026, Vibe Code Bench (v1.1) is maintained by Vals AI. Metric accuracy (%). Ceiling 100. Saturation unknown. Contamination risk low.
- Maintainer
- Vals AI
- Metric
- accuracy (%)
- Ceiling
- 100
- Saturation
- unknown
- Contamination
- low
- Cadence
- Declared cadence: as Vals updates (checked daily). Catalog snapshots: 1, latest Nov 3, 2026.
- Source
- Vals AI · this benchmark on Vals AI
- Grading
- AI judge (browser agent runs the app's workflows) — Models build a web app from a spec; a Browser Use agent clicks through each required workflow.
Source: Vals AI. A proprietary private test set run by Vals; scores are republished with permission. Rows are dated the day isitsota first saw them, and only the benchmark's standard harness counts.
Categories
Where it counts
- Coding › Web dev — secondary, weight 0.35
Top 5
Current top scores
- Claude Sonnet 5.5 · 92.392 · Nov 3, 2026
- Gemini 4 Argon · 91.906 · Nov 3, 2026
- Claude Haiku 5.5 · 90.444 · Nov 3, 2026
- Claude Fable 5 · 90.352 · Nov 3, 2026
- Claude Opus 5.5 · 90.294 · Nov 3, 2026
| Model | Score | Date | Kind |
|---|---|---|---|
| Claude Sonnet 5.5 | 92.392 | 2026-11-03 | snapshot |
| Gemini 4 Argon | 91.906 | 2026-11-03 | snapshot |
| Claude Haiku 5.5 | 90.444 | 2026-11-03 | snapshot |
| Claude Fable 5 | 90.352 | 2026-11-03 | snapshot |
| Claude Opus 5.5 | 90.294 | 2026-11-03 | snapshot |
| Claude Fable 5.1 | 90.263 | 2026-11-03 | snapshot |
| GPT-6 Astra | 89.594 | 2026-11-03 | snapshot |
| GPT-6.1 Sol | 88.931 | 2026-11-03 | snapshot |
| Claude Opus 5 | 88.404 | 2026-11-03 | snapshot |
| GPT-6 Sol | 87.824 | 2026-11-03 | snapshot |
| DeepSeek V4.1 Flash 1017 | 87.73 | 2026-11-03 | snapshot |
| Grok 4.7 | 86.175 | 2026-11-03 | snapshot |
| Muse Wonder Full | 85.996 | 2026-11-03 | snapshot |
| Muse Spark 1.3 | 85.856 | 2026-11-03 | snapshot |
| Mimo V2.6 Pro | 85.223 | 2026-11-03 | snapshot |
| Kimi K3 | 84.968 | 2026-11-03 | snapshot |
| DeepSeek V4.1 Flash | 84.739 | 2026-11-03 | snapshot |
| Muse Wonder | 83.089 | 2026-11-03 | snapshot |
| Muse Spark 1.3 | 82.859 | 2026-11-03 | snapshot |
| Claude Opus 4.8 | 82.725 | 2026-11-03 | snapshot |
| DeepSeek V4 Pro 0813 | 82.297 | 2026-11-03 | snapshot |
| GPT-6 Luna | 81.649 | 2026-11-03 | snapshot |
| Claude Sonnet 5 | 81.325 | 2026-11-03 | snapshot |
| GPT-5.6 Sol | 80.495 | 2026-11-03 | snapshot |
| Muse Spark 1.2 | 79.1 | 2026-11-03 | snapshot |
| Mimo V2.6 Flash | 78.96 | 2026-11-03 | snapshot |
| Gemini 3.8 Flash | 78.651 | 2026-11-03 | snapshot |
| Mistral Large 4 | 78.403 | 2026-11-03 | snapshot |
| GLM 5.3 | 78.125 | 2026-11-03 | snapshot |
| Hy4 Preview | 77.478 | 2026-11-03 | snapshot |