Benchmarks · safety
CyberBench v1.1
Agent performance reproducing OSS-Fuzz vulnerabilities with proof-of-concept inputs and patching the underlying bugs.
37 models · 38 results · updated 2026-10-20 · vals.ai ↗
Leaderboard
GPT-6 Sol max
More from this benchmark
1 published measuresTime per task47 results · lower is better
All results
38 rows| # | Model | Effort | CyberBench v1.1 | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Sol | max | 78.0% | $0.083 | $1.34 | 12 min |
| 2 | Gemini 4 Argon | high | 77.9% | $1.82 | $5.11 | 19 min |
| 3 | GPT-5.6 Sol | max | 76.3% | $0.17 | $3.05 | 11 min |
| 4 | GPT-6 Luna | max | 76.3% | $0.020 | $0.13 | 16 min |
| 5 | Haiku 5.5 | max | 75.5% | $0.026 | $1.25 | 33 min |
| 6 | MiMo V2.6 Flash | high | 75.4% | free | $0.046 | 28 min |
| 7 | Kimi K3 | max | 75.2% | $0.16 | $2.13 | 31 min |
| 8 | DeepSeek V4.1 Flash | high | 73.7% | $0.007 | $0.11 | 14 min |
| 9 | GPT-5.6 Luna | max | 73.6% | $0.038 | $0.40 | 16 min |
| 10 | DeepSeek V4 Pro 0813 | max | 72.9% | $0.59 | $0.59 | 23 min |
| 11 | MiMo V2.6 Pro | high | 72.9% | $0.079 | $0.094 | 28 min |
| 12 | Muse Spark 1.3 | max | 72.7% | $1.67 | $3.34 | 16 min |
| 13 | DeepSeek V4 Flash 0731 | high | 72.1% | $0.19 | $0.19 | 15 min |
| 14 | GLM 5.3 | max | 72.1% | $0.28 | $2.69 | 30 min |
| 15 | GPT-5.6 Terra | max | 72.1% | $0.18 | $3.31 | 17 min |
| 16 | Grok 4.5 | high | 71.0% | $0.46 | $2.95 | 14 min |
| 17 | Fable 5.1 | max | 70.4% | $0.63 | $4.01 | 19 min |
| 18 | Muse Spark 1.2 | xhigh | 69.5% | $1.07 | $2.15 | 20 min |
| 19 | Grok 4.7 | xhigh | 69.5% | $0.79 | $8.54 | 16 min |
| 20 | Muse Spark 1.3 | xhigh | 69.4% | $2.13 | $4.26 | 25 min |
| 21 | GLM 5.3 Flash | max | 67.9% | free | $0.14 | 36 min |
| 22 | Qwen 3.8 27B | xhigh | 67.8% | $0.072 | $0.99 | 42 min |
| 23 | Grok 4.6 | high | 67.7% | $0.42 | $4.07 | 37 min |
| 24 | Inkling | max | 66.8% | free | $1.46 | 14 min |
| 25 | Opus 5 | max | 65.4% | $0.061 | $3.53 | 19 min |
| 26 | MiniMax M3 | max | 65.0% | $0.57 | $3.41 | 41 min |
| 27 | Inkling Small | max | 64.1% | free | $0.25 | 20 min |
| 28 | Sonnet 5 | max | 61.9% | $0.033 | $1.89 | 17 min |
| 29 | Sonnet 5.5 | max | 59.6% | $0.067 | $4.42 | 34 min |
| 30 | Gemini 3.5 Flash-Lite | high | 59.1% | $0.43 | $0.43 | 18 min |