Benchmarks · coding
Vibe Code Bench v1.1
Can models build web applications from scratch? Vals AI's overall score for Vibe Code Bench v1.1.
75 models · 76 results · updated 2026-10-27 · vals.ai ↗
Leaderboard
Sonnet 5.5 max
More from this benchmark
1 published measuresTime per task121 results · lower is better
All results
76 rows| # | Model | Effort | Vibe Code Bench v1.1 | Subscription $ / task | API $ / task | Time | Harness |
|---|---|---|---|---|---|---|---|
| 1 | Sonnet 5.5 | max | 92.4% | $0.47 | $31 | 1.0 h | OpenHands |
| 2 | Gemini 4 Argon | high | 91.9% | $2.89 | $8.11 | 37 min | OpenHands |
| 3 | Haiku 5.5 | max | 90.4% | $0.13 | $6.07 | 35 min | OpenHands |
| 4 | Fable 5 | max | 90.4% | $4.70 | $42 | 1.0 h | OpenHands |
| 5 | Opus 5.5 | max | 90.3% | $0.88 | $58 | 1.6 h | OpenHands |
| 6 | Fable 5.1 | max | 90.3% | $5.20 | $33 | 58 min | OpenHands |
| 7 | GPT-6 Astra | max | 89.6% | $3.30 | $39 | 39 min | OpenHands |
| 8 | Gemini 4 Carbon | high | 89.1% | $8.25 | $8.25 | 36 min | OpenHands |
| 9 | GPT-6.1 Sol | max | 88.9% | $0.73 | $6.23 | 1.2 h | OpenHands |
| 10 | Opus 5 | max | 88.4% | $0.59 | $34 | 1.5 h | OpenHands |
| 11 | GPT-6 Sol | max | 87.8% | $1.63 | $26 | 39 min | OpenHands |
| 12 | DeepSeek V4.1 Flash 1017 | max | 87.7% | free | $0.58 | 16 min | OpenHands |
| 13 | Grok 4.7 | xhigh | 86.2% | $1.47 | $16 | 36 min | OpenHands |
| 14 | Muse Spark 1.3 | max | 85.9% | $1.27 | $2.54 | 16 min | OpenHands |
| 15 | MiMo V2.6 Pro | high | 85.2% | $0.88 | $1.04 | 1.0 h | OpenHands |
| 16 | Kimi K3 | max | 85.0% | $0.77 | $10 | 17 min | OpenHands |
| 17 | DeepSeek V4.1 Flash | high | 84.7% | $0.025 | $0.41 | 15 min | OpenHands |
| 18 | GPT-6.1 Terra | max | 84.0% | $6.00 | $6.00 | 38 min | OpenHands |
| 19 | Muse Spark 1.3 | xhigh | 82.9% | $1.05 | $2.10 | 13 min | OpenHands |
| 20 | Opus 4.8 | max | 82.7% | $0.47 | $27 | 1.3 h | OpenHands |
| 21 | DeepSeek V4 Pro 0813 | max | 82.3% | $0.36 | $0.36 | 1.1 h | OpenHands |
| 22 | GPT-6 Luna | max | 81.6% | $0.20 | $1.35 | 37 min | OpenHands |
| 23 | Sonnet 5 | max | 81.3% | $0.44 | $25 | 1.1 h | OpenHands |
| 24 | GPT-5.6 Sol | max | 80.5% | $1.84 | $33 | 34 min | OpenHands |
| 25 | Muse Spark 1.2 | xhigh | 79.1% | $0.76 | $1.53 | 20 min | OpenHands |
| 26 | MiMo V2.6 Flash | high | 79.0% | free | $0.56 | 50 min | OpenHands |
| 27 | Gemini 3.8 Flash | high | 78.7% | $0.28 | $6.87 | 8.7 min | OpenHands |
| 28 | Mistral Large 4 | high | 78.4% | $39 | $39 | 2.9 h | OpenHands |
| 29 | GLM 5.3 | max | 78.1% | $1.29 | $12 | 1.1 h | OpenHands |
| 30 | GPT-5.6 Luna | max | 77.1% | $0.068 | $0.73 | 26 min | OpenHands |