Vibe Code Bench leaderboard

Building complete web apps from a plain-language brief, graded on whether the app works. Claude Sonnet 5.5 leads with 92.39%.

Models
110
Leader
Claude Sonnet 5.5
Source
Vals AI
As of
Oct 24, 2026
  1. 1Claude Sonnet 5.592.4%
  2. 2Gemini 4 Argon91.9%
  3. 3Claude Haiku 5.590.4%
  4. 4Claude Fable 590.3%
  5. 5Claude Opus 5.590.3%
  6. 6Claude Fable 5.190.3%
  7. 7GPT-6 Astra89.6%
  8. 8GPT-6.1 Sol88.9%
  9. 9Claude Opus 588.4%
  10. 10GPT-6 Sol87.8%
Vibe Code Bench, accuracy against cost per test
Open weightsProprietaryBest for the price
0%25%50%75%100%$.1$1$10$100Cost per test, log scale →Claude Sonnet 5.5Gemini 4 ArgonMuse Wonder FullMiMo-V2.5

Full leaderboard

RankModelLabAccuracyCost / testHarnessPrice in / out
1Claude Sonnet 5.5Anthropic92.39%$31.25OpenHands$2 / $10
2Gemini 4 ArgonGoogle91.91%$8.11OpenHands$2 / $10
3Claude Haiku 5.5Anthropic90.44%$6.07OpenHands$0.10 / $0.50
4Claude Fable 5Anthropic90.35%$41.71OpenHands$10 / $50
5Claude Opus 5.5Anthropic90.29%$57.92OpenHands$4 / $20
6Claude Fable 5.1Anthropic90.26%$33.37OpenHands$10 / $50
7GPT-6 AstraOpenAI89.59%$38.51OpenHands$10 / $50
8GPT-6.1 SolOpenAI88.93%$6.23OpenHands$2 / $10
9Claude Opus 5Anthropic88.40%$33.88OpenHands$5 / $25
10GPT-6 SolOpenAI87.82%$26.36OpenHands$2 / $10
12Grok 4.7xAI86.17%$15.83OpenHands$2 / $6
13Muse Wonder FullMeta86.00%$2.29OpenHands—
14Muse Spark 1.3 MaxMeta85.86%$2.54OpenHands—
15MiMo-V2.6-ProXiaomi85.22%$1.04OpenHands$0.43 / $0.87
16Kimi K3Moonshot AI84.97%$10.01OpenHands$0.24 / $11
17Kimi K3.1 ProMoonshot AI84.89%$7.49OpenHands$2 / $10
18DeepSeek-V4.1-Flash-20260910DeepSeek84.74%$0.41OpenHands$0.15 / $0.60
19Ember-1Fireworks AI83.87%$8.56OpenHands$3 / $15
20Muse WonderMeta83.09%$1.80OpenHands$4 / $20
21Muse Spark 1.3Meta82.86%$2.10OpenHands$1.25 / $4.25
22Claude Opus 4.8Anthropic82.72%$26.88OpenHands$5 / $25
24GPT-6 LunaOpenAI81.65%$1.35OpenHands$0.10 / $0.50
25Claude Sonnet 5Anthropic81.33%$25.39OpenHands$2 / $10
26GPT-5.6 SolOpenAI80.50%$33.40OpenHands$4 / $20
27Muse Spark 1.2Meta79.10%$1.53OpenHands$1.25 / $4.25
28MiMo-V2.6-FlashXiaomi78.96%$0.56OpenHands$0.14 / $0.28
29Gemini 3.8 FlashGoogle78.65%$6.87OpenHands$0.82 / $4.13
30Mistral Large 4Mistral AI78.40%$39.46OpenHands$1.36 / $4.18
31GLM-5.3Z.ai78.13%$12.45OpenHands$0.079 / $1.40
32Hy4 previewTencent77.48%$2.18OpenHands$0.75 / $2.25
34GPT-5.6 LunaOpenAI77.06%$0.73OpenHands$0.20 / $1.20
35Grok 4.6xAI76.24%$4.88OpenHands$2 / $6
36Muse Spark OpenMeta76.19%$1.66OpenHands$1.25 / $4.25
37DeepSeek-V4-FlashDeepSeek74.74%$0.91OpenHands$0.042 / $0.18
38GPT-5.6 TerraOpenAI74.59%$7.89OpenHands$2 / $12
39MiniMax-M3.1-FlashMiniMax73.94%$1.15OpenHands$0.15 / $0.60
40Muse Spark 1.1Meta72.16%$0.92OpenHands$1.25 / $4.25
41Claude Opus 4.7Anthropic71.00%$21.41OpenHands$5 / $25
42Step 5 PreviewStepFun70.40%$5.86OpenHands$1 / $2.70
43Gemini 3.7 FlashGoogle70.39%$4.83OpenHands$0.75 / $3.75
44GPT-5.5OpenAI69.85%$16.66OpenHands$5 / $30
45Grok 4.5xAI69.00%$4.10OpenHands$2 / $6
47Beam 1.0Reflection AI66.44%N/AOpenHands—
48Qwen3.8-27BAlibaba64.85%$23.46OpenHands$0.20 / $2.50
49Qwen3.8-MaxAlibaba64.70%$8.24OpenHands$2 / $6
50Gemini 3.6 FlashGoogle64.00%$3.04OpenHands$0.75 / $3.75
51GLM-5.2Z.ai63.96%$8.49OpenHands$0.034 / $7
52GPT-5.3-CodexOpenAI61.77%$11.91OpenHands$1.75 / $14
53Mercury 3Inception60.93%$0.63OpenHands$0.10 / $0.35
55Claude Sonnet 4.6Anthropic55.77%$7.35Claude Code$3 / $15
56GPT-5.2OpenAI53.50%$17.75OpenHands$1.75 / $14
57Claude Opus 4.6Anthropic53.50%$8.28OpenHands$5 / $25
58DeepSeek-V4-ProDeepSeek49.93%$2.21OpenHands$0.66 / $1.98
59Composer 2.5—49.61%$0.50Cursor CLI—
60Gemini 3.5 FlashGoogle48.68%$2.54OpenHands$1.50 / $9
61GPT-5.4OpenAI48.47%$7.51Codex$2.50 / $15
62GPT-5.4 miniOpenAI47.97%$1.19OpenHands$0.75 / $4.50
63Qwen3.7-Max-PreviewAlibaba47.67%$11.40OpenHands$1.48 / $4.42
64MiniMax-M3MiniMax47.57%$6.45OpenHands$0.30 / $1.20
65Kimi K2.7 CodeMoonshot AI47.21%$3.84OpenHands$0.67 / $3.35
66Qwen3.7-PlusAlibaba46.39%$1.08OpenHands$0.32 / $1.28
67MiMo-V2.5Xiaomi42.17%$0.07OpenHands$0.12 / $0.24
68GPT-5.2-CodexOpenAI37.91%$4.15OpenHands$1.75 / $14
69Kimi K2.6Moonshot AI37.89%$1.93OpenHands$0.65 / $3.41
70Gemini 3.5 Flash-LiteGoogle37.16%$0.83OpenHands$0.30 / $2.50
71MiMo-V2.5-ProXiaomi34.11%$0.17OpenHands$0.30 / $0.61
72Gemini 3.1 Pro PreviewGoogle32.03%$3.83OpenHands$2 / $12
73GLM-5.1Z.ai31.46%$2.89OpenHands$1.40 / $4.40
74GLM-5.3-FlashZ.ai30.76%$2.35OpenHands$0.15 / $0.50
75GPT-5.4 nanoOpenAI26.10%$1.28OpenHands$0.20 / $1.25
76Qwen3.6-PlusAlibaba25.57%$5.45OpenHands$0.33 / $1.95
77GPT-5.1OpenAI24.61%$2.57OpenHands$1.25 / $10
78GLM-5Z.ai23.36%$40.27OpenHands$1 / $3.20
79Claude Sonnet 4.5Anthropic22.62%$6.66OpenHands$3 / $15
80GPT 5.1 Codex MaxOpenAI22.17%$7.32OpenHands$1.25 / $10
81Claude Opus 4.5Anthropic20.63%$32.87OpenHands$5 / $25
82Gemini 3 FlashGoogle20.20%$0.94OpenHands$0.50 / $3
83GPT-5OpenAI20.09%$1.53OpenHands$1.25 / $10
84Muse SparkMeta19.67%N/AOpenHands—
85Grok 4.3xAI19.40%$1.28OpenHands$1.25 / $2.50
86InklingThinky19.21%$1.61OpenHands$1 / $4.05
87Inkling-SmallThinky19.05%$0.43OpenHands$0.45 / $1.20
88Kimi K2.5Moonshot AI17.54%$0.88OpenHands$0.50 / $2.50
89Qwen 3.5 PlusAlibaba15.74%$3.80OpenHands$0.30 / $1.80
90MiniMax-M2.5MiniMax14.85%$2.20OpenHands$0.30 / $1.20
91Gemini 3 ProGoogle14.30%$6.42OpenHands—
92GPT-5 miniOpenAI14.17%$0.25OpenHands$0.25 / $2
93Grok Build 0.1xAI13.35%N/AGrok Build$1 / $2
94GPT-5.1-CodexOpenAI13.12%$3.80OpenHands$1.25 / $10
95Qwen 3.6 27BAlibaba11.94%$4.66OpenHands$0.25 / $2
96MiniMax-M2.7MiniMax11.93%$2.82OpenHands$0.30 / $1.20
97Claude Haiku 4.5Anthropic11.39%$1.31OpenHands$1 / $5
98Laguna M.1Poolside11.04%N/AOpenHands—
99Nemotron 3 UltraNVIDIA7.64%N/AOpenHands$0.60 / $2.40
100SWE-1.6 Fast—7.22%N/ADevin CLI—
101Laguna XS.2Poolside5.21%N/AOpenHands—
102DeepSeek-V3.2-ExpDeepSeek5.11%$2.47OpenHands$0.28 / $0.42
103Grok 4.20xAI4.06%$0.77OpenHands$1.25 / $2.50
104Mercury 2.5Inception3.68%$0.38OpenHands$0.04 / $0.15
105Qwen3-Max-PreviewAlibaba3.51%$6.02OpenHands—
106Ling 3.0 Flash Fin—3.40%$0.23OpenHands—
107GLM-4.6Z.ai3.09%$10.85OpenHands$0.55 / $2.20
108Ling 3.0 FlashinclusionAI2.91%$0.29OpenHands$0.021 / $0.063
109Mistral Medium 3.5Mistral AI2.89%$16.74OpenHands$1.50 / $7.50
110Grok 4.1 FastxAI1.20%$0.21OpenHands—
111Gemini 2.5 ProGoogle0.40%$1.22OpenHands$1.25 / $10
112Gemini 3.1 Flash-Lite PreviewGoogle0.00%$0.51OpenHands$0.25 / $1.50
113Nemotron 3.5 LightningFireworks AI0.00%$0.13OpenHands$0.07 / $0.20
114Grok 4 FastxAI0.00%$0.13OpenHands—
115Mistral Small 4Mistral AI0.00%$6.47OpenHands$0.15 / $0.60

Related leaderboards

Sources

  • Vals AI, as of Oct 24, 2026
  • Provider list prices, as of Oct 24, 2026

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.