Vibe Code Bench v1.1

Can models build web applications from scratch?

ModelsModels with a result.92
Top resultBest result on this test.90.4%Claude Fable 5
Top-3 spreadPoints from first to third.0.8 pts
UpdatedDate the source changed the results.21 Sept 2026

Result and cost

020406080100$0.03$0.1$0.3$1$3$10$30$100RESULTUS DOLLARS PER TASK · LOG SCALE

Results

92 results
#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.
01Claude Fable 5OpenHands90.4%$41.7162 min
02Claude Fable 5.1OpenHands90.3%$33.3758 min
03GPT-6 AstraOpenHands89.6%$38.5139 min
04Claude Opus 5OpenHands88.4%$33.8888 min
05Grok 4.7OpenHands86.2%$15.8336 min
06Muse Spark 1.3 MaxOpenHands85.9%$2.5416 min
07DeepSeek V4.1 FlashOpenHands84.7%$0.40715 min
08Muse Spark 1.3OpenHands82.9%$2.113 min
09Claude Opus 4.8OpenHands82.7%$26.8876 min
10Claude Sonnet 5OpenHands81.3%$38.0867 min
11GPT-5.6 SolOpenHands80.5%$33.434 min
12Muse Spark 1.2OpenHands79.1%$1.5320 min
13Gemini 3.8 FlashOpenHands78.7%$6.879 min
14GLM-5.3OpenHands78.1%$12.4564 min
16Hy4 previewOpenHands77.5%$2.1842 min
17GPT-5.6 LunaOpenHands77.1%$0.72626 min
18Grok 4.6OpenHands76.2%$4.8826 min
20GPT-5.6 TerraOpenHands74.6%$7.8919 min
21Muse Spark 1.1OpenHands72.2%$0.92310 min
22Claude Opus 4.7OpenHands71.0%$21.4136 min
23Gemini 3.7 FlashOpenHands70.4%$4.8324 min
24GPT-5.5OpenHands69.8%$16.6632 min
25Grok 4.5OpenHands69.0%$4.114 min
26GPT-5.5 FactoryFactory67.4%$5.9320 min
28Qwen3.8-27BOpenHands64.8%$23.4644 min
29Qwen3.8 MaxOpenHands64.7%$8.242.8 h
30Gemini 3.6 FlashOpenHands64.0%$3.0425 min
31GLM-5.2OpenHands64.0%$8.4962 min
32GPT-5.3 CodexOpenHands61.8%$11.9176 min
33GPT-5.5 CodexCodex58.2%$3.6312 min
34GPT-5.4OpenHands57.9%$10.6986 min
35Claude Opus 4.6OpenHands57.6%$8.6921 min
37GPT-5.2OpenHands53.5%$17.7583 min
39Claude Sonnet 4.6OpenHands51.5%$5.9126 min
40Composer 2.5Cursor CLI49.6%$0.50210 min
41Gemini 3.5 FlashOpenHands48.7%$2.5415 min
42GPT-5.4 miniOpenHands48.0%$1.1934 min
43Qwen3.7 MaxOpenHands47.7%$11.478 min
44MiniMax M3OpenHands47.6%$6.4585 min
45Kimi K2.7 CodeOpenHands47.2%$3.842.9 h
46Qwen3.7 PlusOpenHands46.4%$1.0837 min
47MiMo-V2.5OpenHands42.2%$0.06826 min
48GPT-5.2-CodexOpenHands37.9%$4.1532 min
50MiMo-V2.5-ProOpenHands34.1%$0.16740 min
52GLM-5.1OpenHands31.5%$2.8934 min
53GLM-5.3-FlashOpenHands30.8%$2.3584 min
54GPT-5.4 nanoOpenHands26.1%$1.2855 min
55Qwen3.6 PlusOpenHands25.6%$5.4538 min
56GPT-5.1OpenHands24.6%$2.5731 min
57GLM-5 ThinkingOpenHands23.4%$40.273.7 h
62GPT-5OpenHands20.1%$1.5331 min
63Muse SparkOpenHands19.7%$0.5816 min
64Grok 4.3OpenHands19.4%$1.2810 min
65InklingOpenHands19.2%$1.6118 min
66Inkling-SmallOpenHands19.1%$0.43249 min
69MiniMax M2.5OpenHands14.9%$2.251 min
70Gemini 3 ProOpenHands14.3%$6.422.9 h
71GPT-5 miniOpenHands14.2%$0.24912 min
73GPT-5.1-CodexOpenHands13.1%$3.850 min
74Qwen3.6-27BOpenHands11.9%$4.662.7 h
75MiniMax M2.7OpenHands11.9%$2.8223 min
77Laguna M.1OpenHands11.0%$2.0640 min
79Laguna XS.2OpenHands5.2%$0.98137 min
82Mercury 2.5OpenHands3.7%$0.3783 min
83Qwen3 MaxOpenHands3.5%$6.0258 min
84GLM-4.6OpenHands3.1%$10.852.8 h
85Ling 3.0 FlashOpenHands2.9%$0.29217 min
86Mistral Medium 3.5OpenHands2.9%$16.7441 min
88Gemini 2.5 ProOpenHands0.4%$1.2235 min
89Mistral SmallOpenHands0.0%$6.4730 min