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.

104models
–Open Index weight
2026-10-12last updated
Vals AIpublisher

Vibe Code Bench v1.1

Higher is better · best effort per model

Chart settings
104 of 104 selected

full table below

#ModelEffortScoreCost / taskHarness
1Sonnet 5.5max92.4%$31.25OpenHands
2Gemini 4high91.9%$8.11OpenHands
3Haiku 5.5max90.4%$6.07OpenHands
4Fable 5max90.4%$41.71OpenHands
5Opus 5.5max90.3%$57.92OpenHands
6Fable 5.1max90.3%$33.37OpenHands
7GPT-6 Astramax89.6%$38.51OpenHands
8GPT-6.1 Solmax88.9%$6.23OpenHands
9Opus 5max88.4%$33.88OpenHands
10GPT-6 Solmax87.8%$26.36OpenHands
11Grok 4.7xhigh86.2%$15.83OpenHands
12Wonder Fullmax86.0%$2.29OpenHands
13Muse Spark 1.3max85.9%$2.54OpenHands
14MiMo V2.6 Prohigh85.2%$1.04OpenHands
15Kimi K3max85.0%$10.01OpenHands
16DeepSeek V4.1 Flashhigh84.7%$0.407OpenHands
17Ember-1–83.9%$8.56OpenHands
18Wondermax83.1%$1.80OpenHands
19Opus 4.8max82.7%$26.88OpenHands
20DeepSeek V4 Pro 0813max82.3%$0.356OpenHands
21GPT-6 Lunamax81.6%$1.35OpenHands
22Sonnet 5max81.3%$25.39OpenHands
23GPT-5.6 Solmax80.5%$33.40OpenHands
24Muse Spark 1.2xhigh79.1%$1.53OpenHands
25MiMo V2.6 Flashhigh79.0%$0.563OpenHands
26Gemini 3.8 Flashhigh78.7%$6.87OpenHands
27Mistral Large 4high78.4%$39.46OpenHands
28GLM 5.3max78.1%$12.45OpenHands
29Hy4–77.5%$2.18OpenHands
30GPT-5.6 Lunamax77.1%$0.726OpenHands
31Grok 4.6high76.2%$4.88OpenHands
32DeepSeek V4 Flash 0731high74.7%$0.906OpenHands
33GPT-5.6 Terramax74.6%$7.89OpenHands
34Muse Spark 1.1xhigh72.2%$0.923OpenHands
35Opus 4.7max71.0%$21.41OpenHands
36Step 5 Preview–70.4%$5.86OpenHands
37Gemini 3.7 Flashhigh70.4%$4.83OpenHands
38GPT-5.5xhigh69.8%$16.66OpenHands
39Grok 4.5high69.0%$4.10OpenHands
40GPT-5.4xhigh67.4%$10.69OpenHands
41Qwen 3.8 27Bxhigh64.8%$23.46OpenHands
42Qwen 3.8 Maxmax64.7%$8.24OpenHands
43Gemini 3.6 Flashhigh64.0%$3.04OpenHands
44GLM 5.2max64.0%$8.49OpenHands
45GPT-5.3 Codexxhigh61.8%$11.91OpenHands
46Opus 4.6max57.6%$8.69OpenHands
47Sonnet 4.6max55.8%$7.35Claude Code
48GPT-5.2xhigh53.5%$17.75OpenHands
49DeepSeek V4max49.9%$2.21OpenHands
50Composer 2.5none49.6%$0.502Cursor CLI
51Gemini 3.5 Flashhigh48.7%$2.54OpenHands
52GPT-5.4 Minixhigh48.0%$1.19OpenHands
53Qwen 3.7 Maxmax47.7%$11.40OpenHands
54MiniMax M3max47.6%$6.45OpenHands
55Kimi K2.7 Codemax47.2%$3.84OpenHands
56Qwen 3.7 Plushigh46.4%$1.08OpenHands
57MiMo V2.5xhigh42.2%$0.068OpenHands
58GPT-5.2 Codexhigh37.9%$4.15OpenHands
59Kimi K2.6max37.9%$1.93OpenHands
60Gemini 3.5 Flash-Litehigh37.2%$0.833OpenHands
61MiMo V2.5 Proxhigh34.1%$0.167OpenHands
62Gemini 3.1 Prohigh32.0%$3.83OpenHands
63GLM 5.1max31.5%$2.89OpenHands
64GLM 5.3 Flashmax30.8%$2.35OpenHands
65GPT-5.4 Nanohigh26.1%$1.28OpenHands
66Qwen 3.6 Plusmax25.6%$5.45OpenHands
67GPT-5.1high24.6%$2.57OpenHands
68GLM 5high23.4%$40.27OpenHands
69Sonnet 4.5high22.6%$6.66OpenHands
70GPT-5.1 Codexhigh22.2%$7.32OpenHands
71Opus 4.5high20.6%$32.87OpenHands
72Gemini 3 Flashhigh20.2%$0.942OpenHands
73GPT-5high20.1%$1.53OpenHands
74Muse Spark–19.7%$0.580OpenHands
75Grok 4.3high19.4%$1.28OpenHands
76Inklingmax19.2%$1.61OpenHands
77Inkling Smallxhigh19.1%$0.432OpenHands
78Kimi K2.5max17.5%$0.879OpenHands
79Qwen 3.5 Plusnone15.7%$3.80OpenHands
80MiniMax M2.5high14.9%$2.20OpenHands
81Gemini 3 Prohigh14.3%$6.42OpenHands
82GPT-5 Minihigh14.2%$0.249OpenHands
83Grok Build 0.1–13.3%–Grok Build
84Qwen 3.6 27Bmax11.9%$4.66OpenHands
85MiniMax M2.7high11.9%$2.82OpenHands
86Haiku 4.5xhigh11.4%$1.31OpenHands
87Laguna M.1–11.0%$2.06OpenHands
88Nemotron 3 Ultra 550B A55Bmax7.6%–OpenHands
89SWE 1.6none7.2%–Devin CLI
90Laguna XS.2–5.2%$0.981OpenHands
91DeepSeek V3.2high5.1%$2.47OpenHands
92Grok 4.20xhigh4.1%$0.772OpenHands
93Mercury 2.5high3.7%$0.378OpenHands
94Qwen 3 Maxmax3.5%$6.02OpenHands
95Ling 3.0 Flash Fin–3.4%$0.233OpenHands
96GLM 4.6none3.1%$10.85OpenHands
97Ling 3.0 Flash–2.9%$0.292OpenHands
98Mistral Medium 3.5high2.9%$16.74OpenHands
99Grok 4.1 Fasthigh1.2%$0.209OpenHands
100Gemini 2.5 Prohigh0.4%$1.22OpenHands
101Gemini 3.1 Flash-Litehigh0.0%$0.510OpenHands
102Nemotron 3.5 Lightning–0.0%$0.129OpenHands
103Grok 4 Fastnone0.0%$0.133OpenHands
104Mistral Small 4high0.0%$6.47OpenHands