CyberBench
As of Nov 3, 2026, CyberBench (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
- Automatic (tests or exact checks) — PoC inputs must trigger the OSS-Fuzz crash; patches must fix it under a clean-room grader.
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
- Cybersecurity — primary, weight 1
Top 5
Current top scores
- Muse Wonder · 80.357 · Nov 3, 2026
- GPT-6 Sol · 77.976 · Nov 3, 2026
- Gemini 4 Argon · 77.857 · Nov 3, 2026
- GPT-5.6 Sol · 76.31 · Nov 3, 2026
- GPT-6 Luna · 76.25 · Nov 3, 2026
| Model | Score | Date | Kind |
|---|---|---|---|
| Muse Wonder | 80.357 | 2026-11-03 | snapshot |
| GPT-6 Sol | 77.976 | 2026-11-03 | snapshot |
| Gemini 4 Argon | 77.857 | 2026-11-03 | snapshot |
| GPT-5.6 Sol | 76.31 | 2026-11-03 | snapshot |
| GPT-6 Luna | 76.25 | 2026-11-03 | snapshot |
| Claude Haiku 5.5 | 75.476 | 2026-11-03 | snapshot |
| Mimo V2.6 Flash | 75.357 | 2026-11-03 | snapshot |
| Kimi K3 | 75.238 | 2026-11-03 | snapshot |
| DeepSeek V4.1 Flash | 73.69 | 2026-11-03 | snapshot |
| GPT-5.6 Luna | 73.631 | 2026-11-03 | snapshot |
| Muse Wonder Full | 73.631 | 2026-11-03 | snapshot |
| DeepSeek V4 Pro 0813 | 72.857 | 2026-11-03 | snapshot |
| Mimo V2.6 Pro | 72.857 | 2026-11-03 | snapshot |
| Muse Spark 1.3 | 72.738 | 2026-11-03 | snapshot |
| DeepSeek V4 Flash 0731 | 72.084 | 2026-11-03 | snapshot |
| GPT-5.6 Terra | 72.084 | 2026-11-03 | snapshot |
| GLM 5.3 | 72.084 | 2026-11-03 | snapshot |
| Grok 4.5 | 71.012 | 2026-11-03 | snapshot |
| Claude Fable 5.1 | 70.416 | 2026-11-03 | snapshot |
| Muse Spark 1.2 | 69.524 | 2026-11-03 | snapshot |
| Grok 4.7 | 69.464 | 2026-11-03 | snapshot |
| Muse Spark 1.3 | 69.405 | 2026-11-03 | snapshot |
| GLM 5.3 Flash | 67.857 | 2026-11-03 | snapshot |
| Qwen3.8 27B | 67.798 | 2026-11-03 | snapshot |
| Grok 4.6 | 67.678 | 2026-11-03 | snapshot |
| Inkling | 66.786 | 2026-11-03 | snapshot |
| Claude Opus 5 | 65.357 | 2026-11-03 | snapshot |
| Hy4 Preview | 65.357 | 2026-11-03 | snapshot |
| Minimax M3 | 65 | 2026-11-03 | snapshot |
| Inkling Small | 64.107 | 2026-11-03 | snapshot |