Vibe Code Bench v1.1

Can models build web applications from scratch?

ModelsModels with a result.123
Top resultBest result on this benchmark.93.8%Claude Fable 5.2
Top-3 spreadPoints from first to third.1.9 pts
UpdatedDate the source changed the results.9 Nov 2026

Result and cost

120 of 123 results

Results

123 results
#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.
01Claude Fable 5.2OpenHands93.8% ±1.2$22.1341 min
02Claude Sonnet 5.5OpenHands92.4% ±1.3$19.7361 min
03Gemini 4 ArgonOpenHands91.9% ±1.9$8.1137 min
04Claude Haiku 5.5OpenHands90.4% ±1.7$6.0735 min
04Claude Fable 5OpenHands90.4% ±2.1$41.7162 min
06Claude Opus 5.5OpenHands90.3% ±1.5$35.771.6 h
06Claude Fable 5.1OpenHands90.3% ±1.6$33.3758 min
08GPT-6 AstraOpenHands89.6% ±2.2$38.5139 min
09Gemini 4 CarbonOpenHands89.1% ±2.3$8.2536 min
10GPT-6.1 SolOpenHands88.9% ±1.9$6.2375 min
11Claude Opus 5OpenHands88.4% ±3.0$33.8888 min
12GPT-6 SolOpenHands87.8% ±2.5$26.3639 min
13Grok 4.7OpenHands86.2% ±2.2$15.8336 min
14Muse Wonder FullOpenHands86.0% ±1.9$2.2911 min
15Muse Spark 1.3 MaxOpenHands85.9% ±2.5$2.5416 min
16MiMo-V2.6-ProOpenHands85.2% ±3.4$1.0461 min
17Kimi K3OpenHands85.0% ±2.7$10.0117 min
18DeepSeek V4.1 Flash 1017OpenHands84.7% ±2.9$0.40715 min
19GPT-6.1 TerraOpenHands84.0% ±2.9$6.0038 min
20Ember-1OpenHands83.9% ±3.2$8.5639 min
21Muse EmberOpenHands83.7% ±2.8$0.0543 min
22Muse WonderOpenHands83.1% ±2.5$1.806 min
23Muse Spark 1.3OpenHands82.9% ±2.9$2.1013 min
24Claude Opus 4.8OpenHands82.7% ±3.1$26.8876 min
25DeepSeek V4 Pro 0813OpenHands82.3% ±3.1$0.35666 min
26GPT-6 LunaOpenHands81.6% ±3.4$1.3537 min
26Mistral Large 4 OSSOpenHands81.6% ±3.3$11.7250 min
28Inkling 2 SmallOpenHands81.5% ±3.5$1.9026 min
29Claude Sonnet 5OpenHands81.3% ±3.0$25.3967 min
30Hy4OpenHands81.0% ±3.5$2.3938 min
31GPT-5.6 SolOpenHands80.5% ±3.7$33.4034 min
32Muse Spark 1.2OpenHands79.1% ±3.3$1.5320 min
33MiMo-V2.6-FlashOpenHands79.0% ±4.0$0.56350 min
34Gemini 3.8 FlashOpenHands78.7% ±3.9$6.879 min
35Mistral Large 4OpenHands78.4% ±3.5$20.282.9 h
36GLM-5.3OpenHands78.1% ±3.9$12.4564 min
37Hy4 previewOpenHands77.5% ±4.0$2.1842 min
39Qwen3.8 Max InternalOpenHands77.1% ±3.7$11.6785 min
39GPT-5.6 LunaOpenHands77.1% ±3.1$0.72626 min
41Grok 4.6OpenHands76.2% ±3.8$4.8826 min
41Muse Spark OpenOpenHands76.2% ±3.3$1.6631 min
43DeepSeek V4 Flash 0731OpenHands74.7% ±3.4$0.90637 min
44GPT-5.6 TerraOpenHands74.6% ±4.2$7.8919 min
45MiniMax M3.1 FlashOpenHands73.9% ±4.2$1.1521 min
46Muse Spark 1.1OpenHands72.2% ±3.3$0.92310 min
47Claude Opus 4.7OpenHands71.0% ±4.5$21.4136 min
48Step 5 PreviewOpenHands70.4% ±4.3$5.861.5 h
48Gemini 3.7 FlashOpenHands70.4% ±4.8$4.8324 min
50GPT-5.5OpenHands69.8% ±4.5$16.6632 min
51Grok 4.5OpenHands69.0% ±4.5$4.1014 min
52GPT-5.5 FactoryFactory67.4% ±4.8$5.9320 min
53Beam 1.0OpenHands66.4% ±4.1—2 min
54Qwen3.8-27BOpenHands64.8% ±4.8$23.4644 min
55Qwen3.8 MaxOpenHands64.7% ±5.4$8.242.8 h
56Gemini 3.6 FlashOpenHands64.0% ±4.3$3.0425 min
56GLM-5.2OpenHands64.0% ±4.8$8.4962 min
58GPT-5.3 CodexOpenHands61.8% ±4.7$11.9176 min
59Mercury 3OpenHands60.9% ±5.4$0.6279 min
60GPT-5.5 CodexCodex58.2% ±4.9$3.6312 min
61Claude Opus 4.6OpenHands57.6% ±4.4$8.6921 min
63GPT-5.2OpenHands53.5% ±5.1$17.7583 min
63Claude Opus 4.6 (Adaptive)OpenHands53.5% ±4.7$8.2823 min
65Claude Sonnet 4.6OpenHands51.5% ±4.6$5.9126 min
66DeepSeek V4 Pro 0423OpenHands49.9% ±4.8$2.2157 min
67Composer 2.5Cursor CLI49.6% ±5.0$0.50210 min
68Gemini 3.5 FlashOpenHands48.7% ±4.7$2.5415 min
69GPT-5.4Codex48.5% ±5.1$7.5118 min
70GPT-5.4 miniOpenHands48.0% ±5.6$1.1934 min
71Qwen3.7 MaxOpenHands47.7% ±4.6$11.4078 min
72MiniMax M3OpenHands47.6% ±5.4$6.4585 min
73Kimi K2.7 CodeOpenHands47.2% ±5.2$3.842.9 h
74Qwen3.7 PlusOpenHands46.4% ±4.6$1.0837 min
75MiMo-V2.5OpenHands42.2% ±4.6$0.06826 min
76GPT-5.2-CodexOpenHands37.9% ±4.6$4.1532 min
76Kimi K2.6OpenHands37.9% ±4.9$1.9349 min
78Gemini 3.5 Flash-LiteOpenHands37.2% ±4.6$0.8338 min
79MiMo-V2.5-ProOpenHands34.1% ±4.5$0.16740 min
80Gemini 3.1 Pro PreviewOpenHands32.0% ±4.3$3.8320 min
81GLM-5.1OpenHands31.5% ±4.6$2.8934 min
82GLM-5.3-FlashOpenHands30.8% ±5.3$4.7084 min
83GPT-5.4 nanoOpenHands26.1% ±5.1$1.2855 min
84Qwen3.6 PlusOpenHands25.6% ±3.9$5.4538 min
85GPT-5.1OpenHands24.6% ±4.3$2.5731 min
86GLM-5 ThinkingOpenHands23.4% ±4.0$40.273.7 h
87Claude Sonnet 4.5 ThinkingOpenHands22.6% ±3.7$6.6649 min
88GPT-5.1-Codex-MaxOpenHands22.2% ±3.8$7.328.7 h
89Claude Opus 4.5 ThinkingOpenHands20.6% ±3.2$32.8738 min
90Gemini 3 Flash PreviewOpenHands20.2% ±3.9$0.94213 min
91GPT-5OpenHands20.1% ±3.4$1.5331 min
92Muse SparkOpenHands19.7% ±4.0$0.5816 min
93Grok 4.3OpenHands19.4% ±4.2$1.2810 min
94InklingOpenHands19.2% ±3.7$1.6118 min
95Inkling-SmallOpenHands19.1% ±3.4$0.43249 min
96Kimi K2.5 ThinkingOpenHands17.5% ±3.3$0.87943 min
97Qwen3.5 Plus ThinkingOpenHands15.7% ±3.2$3.8050 min
98MiniMax M2.5OpenHands14.9% ±3.0$2.2051 min
99Gemini 3 ProOpenHands14.3% ±3.1$6.422.9 h
100GPT-5 miniOpenHands14.2% ±3.5$0.24912 min
101Grok Build 0.1Grok Build13.3% ±3.8—7 min
102GPT-5.1-CodexOpenHands13.1% ±3.2$3.8050 min
103Qwen3.6-27BOpenHands11.9% ±3.4$4.662.7 h
103MiniMax M2.7OpenHands11.9% ±2.9$2.8223 min
105Claude Haiku 4.5 ThinkingOpenHands11.4% ±3.1$1.3113 min
106Laguna M.1OpenHands11.0% ±2.8$2.0640 min
107Swe 1.6 FastDevin CLI7.2% ±2.6—3 min
108Laguna XS.2OpenHands5.2% ±2.2$0.98137 min
109DeepSeek V3.2 (Thinking)OpenHands5.1% ±2.1$2.4756 min
110Grok 4.20 (Reasoning)OpenHands4.1% ±2.1$0.7725 min
111Mercury 2.5OpenHands3.7% ±1.4$0.3783 min
113Qwen3 MaxOpenHands3.5% ±1.3$6.0258 min
114Ling 3.0 Flash Af Rc3OpenHands3.4% ±1.3$0.23324 min
115GLM-4.6OpenHands3.1% ±1.2$10.852.8 h
116Ling 3.0 FlashOpenHands2.9% ±2.1$0.29217 min
116Mistral Medium 3.5OpenHands2.9% ±1.7$16.7441 min
118Grok 4.1 Fast (Reasoning)OpenHands1.2% ±1.2$0.2099 min
119Gemini 2.5 ProOpenHands0.4% ±0.4$1.2235 min
120Mistral Small 4OpenHands0.0%$6.4730 min