Benchmark profile

Vibe Code Bench v1.1 (Vibe Code Bench)

Vals.ai benchmark for evaluating whether models can build complete web applications from natural language specifications in a production-like development environment.

Data verified July 23, 2026

How BenchLM shows Vibe Code Bench v1.1

BenchLM mirrors the public Vals AI Vibe Code Bench v1.1 leaderboard captured from https://www.vals.ai/benchmarks/vibe-code and updated by Vals on July 23, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Vibe Code Bench v1.1 is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

76 Vals rows1 task viewsprivate datasetTasks: OverallDisplay only

Vibe Code Bench v1.1 on Vals AI Vals methodology Vals home

Vibe Code score on Vibe Code Bench — July 23, 2026

BenchLM mirrors the published vibe code score view for Vibe Code Bench. Claude Fable 5 leads the public snapshot at 90.35% , followed by Claude Opus 5 (88.40%) and Kimi K3 (84.96%). BenchLM does not use these results to rank models overall.

Claude Fable 5

Anthropic

OpenHands

anthropic/claude-fable-5

90.35%

Overall —

Claude Opus 5

Anthropic

OpenHands

anthropic/claude-opus-5

88.40%

Overall —

Kimi K3

Moonshot AI

OpenHands

kimi/kimi-k3

84.96%

Overall —

76 modelsCodingCurrentDisplay onlyUpdated July 23, 2026

Vibe Code score table (76 models)

Score

Claude Fable 5AnthropicOpenHands

90.35%

Claude Opus 5AnthropicOpenHands

88.40%

Kimi K3Moonshot AIOpenHands

84.96%

Claude Opus 4.8AnthropicOpenHands

82.72%

Claude Sonnet 5AnthropicOpenHands

81.33%

GPT-5.6 SolOpenAIOpenHands

80.50%

Claude Opus 4.8 Claude CodeAnthropicClaude Code

77.48%

GPT-5.6 LunaOpenAIOpenHands

77.06%

Muse Spark 1.1MetaOpenHands

72.16%

Claude Opus 4.7AnthropicOpenHands

71.00%

GPT-5.5OpenAIOpenHands

69.85%

Grok 4.5xAIOpenHands

69.00%

GPT-5.6 TerraOpenAIOpenHands

67.84%

GPT-5.4OpenAIOpenHands

67.42%

GPT-5.5 FactoryOpenAIFactory

67.39%

GLM 5.2Zhipu AIOpenHands

63.96%

GPT-5.3 CodexOpenAIOpenHands

61.77%

GPT-5.5 CodexOpenAICodex

58.19%

Claude Opus 4.6AnthropicOpenHands

57.57%

Gemini 3.6 FlashGoogleOpenHands

57.32%

Claude Sonnet 4.6 Claude CodeAnthropicClaude Code

55.77%

GPT-5.2OpenAIOpenHands

53.50%

Claude Opus 4.6 ThinkingAnthropicOpenHands

53.50%

Claude Sonnet 4.6AnthropicOpenHands

51.48%

DeepSeek V4 ProDeepSeekOpenHands

49.93%

Composer 2.5CursorCursor CLI

49.61%

Gemini 3.5 FlashGoogleOpenHands

48.68%

GPT-5.4OpenAICodex

48.47%

GPT-5.4 MiniOpenAIOpenHands

47.97%

Qwen3.7 MaxAlibabaOpenHands

47.67%

MiniMax M3MiniMaxOpenHands

47.57%

Kimi K2.7 CodeMoonshot AIOpenHands

47.21%

Qwen3.7 PlusAlibabaOpenHands

46.39%

Mimo V2.5XiaomiOpenHands

42.17%

GPT-5.2 CodexOpenAIOpenHands

37.91%

Kimi K2.6Moonshot AIOpenHands

37.89%

Gemini 3.5 Flash LiteGoogleOpenHands

37.16%

Mimo V2.5 ProXiaomiOpenHands

34.11%

Gemini 3.1 Pro PreviewGoogleOpenHands

32.03%

GLM 5.1Zhipu AIOpenHands

31.46%

GPT-5.4 NanoOpenAIOpenHands

26.10%

Qwen3.6 PlusAlibabaOpenHands

25.57%

GPT-5.1OpenAIOpenHands

24.61%

GLM 5 ThinkingZhipu AIOpenHands

23.36%

Claude Sonnet 4.5 20250929 ThinkingAnthropicOpenHands

22.62%

GPT-5.1 Codex MaxOpenAIOpenHands

22.17%

Claude Opus 4.5 20251101 ThinkingAnthropicOpenHands

20.63%

Gemini 3 Flash PreviewGoogleOpenHands

20.20%

GPT-5OpenAIOpenHands

20.09%

Muse SparkMetaOpenHands

19.67%

Grok 4.3xAIOpenHands

19.40%

InklingThinkingmachinesOpenHands

19.21%

Kimi K2.5 ThinkingMoonshot AIOpenHands

17.54%

Qwen3.5 Plus ThinkingAlibabaOpenHands

15.74%

MiniMax M2.5MiniMaxOpenHands

14.85%

Gemini 3 Pro PreviewGoogleOpenHands

14.30%

GPT-5 MiniOpenAIOpenHands

14.17%

Grok Build 0.1xAIGrok Build

13.35%

GPT-5.1 CodexOpenAIOpenHands

13.12%

Qwen3.6 27bAlibabaOpenHands

11.94%

MiniMax M2.7MiniMaxOpenHands

11.93%

Claude Haiku 4.5 20251001 ThinkingAnthropicOpenHands

11.39%

Laguna M.1PoolsideOpenHands

11.04%

Nemotron 3 Ultra 550b A55bNvidiaOpenHands

7.64%

Swe 1.6 FastDevinDevin CLI

7.22%

Laguna Xs.2PoolsideOpenHands

5.21%

DeepSeek V3p2 ThinkingFireworks AIOpenHands

5.11%

Grok 4.20 0309 ReasoningxAIOpenHands

4.06%

Qwen3 MaxAlibabaOpenHands

3.51%

GLM 4.6Zhipu AIOpenHands

3.09%

Mistral Medium 3.5Mistral AIOpenHands

2.89%

Grok 4.1 Fast ReasoningxAIOpenHands

1.20%

Gemini 2.5 ProGoogleOpenHands

0.40%

Gemini 3.1 Flash Lite PreviewGoogleOpenHands

0.00%

Grok 4 Fast ReasoningxAIOpenHands

0.00%

Mistral Small 2603Mistral AIOpenHands

0.00%

The published Vibe Code Bench snapshot places Claude Fable 5 first at 90.35%. The third row is 5.39 points behind. The broader top-10 range is 19.35 points, so the table still separates the published systems.

76 models have been evaluated on Vibe Code Bench. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Vibe Code Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Vibe Code Bench

Year

2026

Tasks

End-to-end web application builds

Format

Full-stack app implementation benchmark

Difficulty

End-to-end software delivery

Vibe Code Bench v1.1 asks models to build full web apps with services such as Supabase, Stripe test mode, email, browsing, and file editing available. The score is overall application pass accuracy across private end-to-end app tasks.

Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development Public benchmark source

BenchLM freshness & provenance

Version

Vibe Code Bench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does Vibe Code Bench measure?

Vals.ai benchmark for evaluating whether models can build complete web applications from natural language specifications in a production-like development environment.

Which model leads the published Vibe Code Bench snapshot?

Claude Fable 5 currently leads the published Vibe Code Bench snapshot with 90.35% vibe code score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Vibe Code Bench?

76 AI models are included in BenchLM's mirrored Vibe Code Bench snapshot, based on the public leaderboard captured on July 23, 2026.

Last updated: July 23, 2026 · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.