AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    Vibe Code Bench

    🏆 Leaderboard

    As of August 20, 2026, Claude Fable 5 is #1 for Vibe Code Bench at 90.3%. Ranked by the Vibe Code Bench score 59 models in this index have a published Vibe Code Bench score. Vibe Code Bench leaderboard with live API prices. Vibe Code Bench — Vals.ai coding eval for realistic product-style implementation quality, not just unit-test patches.

    Updated August 20, 2026282 models33 providers
    Claude Fable 5
    Anthropic · Proprietary
    		90.3%$60.00
    Claude Opus 5
    Anthropic · Proprietary
    		88.4%$30.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		85.0%$18.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		82.7%$30.00
    DeepSeek-V4-Pro-0813OSS
    DeepSeek · Open Source
    		82.3%$5.28
    Claude Sonnet 5
    Anthropic · Proprietary
    		81.3%$12.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		80.5%$35.00
    Muse Spark 1.2
    Meta · Proprietary
    		79.1%$5.50
    GPT-5.6 Luna
    OpenAI · Proprietary
    		77.1%$1.40
    Grok 4.6
    xAI · Proprietary
    		76.2%$8.00
    DeepSeek-V4-Flash-0731OSS
    DeepSeek · Open Source
    		74.7%$1.76
    Muse Spark 1.1
    Meta · Proprietary
    		72.2%$5.50
    Claude Opus 4.7
    Anthropic · Proprietary
    		71%$30.00
    Gemini 3.7 Flash
    Google · Proprietary
    		70.4%$4.50
    GPT-5.5
    OpenAI · Proprietary
    		69.8%$35.00
    Grok 4.5
    xAI · Proprietary
    		69%$8.00
    GPT-5.6 Terra
    OpenAI · Proprietary
    		67.8%$14.00
    GPT-5.4
    OpenAI · Proprietary
    		67.4%$17.50
    Qwen3.8 MaxOSS
    Qwen · Open Source
    		64.7%$8.00
    Gemini 3.6 Flash
    Google · Proprietary
    		64.0%$4.50
    GLM-5.2OSS
    Z AI · Open Source
    		64.0%$5.80
    GPT-5.3 Codex
    OpenAI · Proprietary
    		61.8%$15.75
    Claude Opus 4.6
    Anthropic · Proprietary
    		57.6%$30.00
    GPT-5.2
    OpenAI · Proprietary
    		53.5%$15.75
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		51.5%$18.00
    Gemini 3.5 Flash
    Google · Proprietary
    		48.7%$10.50
    GPT-5.4 mini
    OpenAI · Proprietary
    		48.0%$5.25
    Qwen3.7 Max
    Qwen · Proprietary
    		47.7%$5.00
    MiniMax M3OSS
    MiniMax · Open Source
    		47.6%$1.50
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		47.2%$4.93
    Qwen3.7-Plus
    Qwen · Proprietary
    		46.4%$1.60
    MiMo-V2.5OSS
    Xiaomi · Open Source
    		42.2%$0.50
    Gemini 2.5 Pro
    Google · Proprietary
    		40%$11.25
    GPT-5.2 Codex
    OpenAI · Proprietary
    		37.9%$15.75
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		37.9%$4.93
    Gemini 3.5 Flash-Lite
    Google · Proprietary
    		37.2%$2.80
    MiMo-V2.5-ProOSS
    Xiaomi · Open Source
    		34.1%$1.30
    Gemini 3.1 Pro
    Google · Proprietary
    		32.0%$17.50
    GLM-5.1OSS
    Z AI · Open Source
    		31.5%$5.80
    GPT-5.4 nano
    OpenAI · Proprietary
    		26.1%$1.45
    Qwen3.6 Plus
    Qwen · Proprietary
    		25.6%$3.50
    GPT-5.1
    OpenAI · Proprietary
    		24.6%$11.25
    GPT-5.1 Codex
    OpenAI · Proprietary
    		22.2%$11.25
    Gemini 3 Flash
    Google · Proprietary
    		20.2%$3.50
    GPT-5
    OpenAI · Proprietary
    		20.1%$11.25
    Grok 4.3
    xAI · Proprietary
    		19.4%$3.75
    Inkling-SmallOSS
    Thinking Machines · Open Source · via Thinking Machines Lab
    		19.1%$1.50
    MiniMax M2.5OSS
    MiniMax · Open Source
    		14.8%$1.50
    Gemini 3 Pro
    Google · Proprietary
    		14.3%$14.00
    GPT-5 mini
    OpenAI · Proprietary
    		14.2%$2.25
    Showing 1–50 of 282 models

    Next step

    You found the model. Now ship the product.

    Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.

    Build with the APIsHave us build it with you

    The index

    All Large Language Models

    282 models across 33 providers. Search or jump to a lab — every model page stays linked here.

    OpenAI51Anthropic22Google25Cursor2xAI15DeepSeek16MiniMax6Qwen38AI21 Labs2Amazon5Baidu1ByteDance2Cohere3IBM1Inception1inclusionAI1LG AI Research1Meituan4Meta12Microsoft5Mistral23Moonshot AI9Nous Research1NVIDIA5Poolside2Sakana AI1StepFun1Tencent1Thinking Machines1Unisound1Upstage1Xiaomi3Z AI20

    Baidu

    1 models
    ERNIE 4.5

    Inception

    1 models
    Mercury 2

    inclusionAI

    1 models
    Ling-3.0-flash

    LG AI Research

    1 models
    K-EXAONE-236B-A23B

    Nous Research

    1 models
    Hermes 3 70B

    Sakana AI

    1 models
    Sakana Namazu

    StepFun

    1 models
    Step-3.5-Flash

    Tencent

    1 models
    Hy3

    Thinking Machines

    1 models
    Inkling-Small

    Unisound

    1 models
    U2

    Upstage

    1 models
    Solar Pro 4

    Which model leads Vibe Code Bench right now?

    As of August 20, 2026, Claude Fable 5 by Anthropic is #1 for Vibe Code Bench at 90.3%. Ranked by the Vibe Code Bench score This board also tracks Vibe Code Bench. Next on the same board: Claude Opus 5 and Kimi K3. This vibe code bench leaderboard ranks models by Vibe Code Bench. Scores come from public evals. Prices are the live API rates in the table above.

    Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)

    Top 8 for vibe code bench. Ranked by the Vibe Code Bench score Input and output are dollars per million tokens.
    RankModelVibe Code BenchInput /MOutput /M
    1Claude Fable 590.3%$10.00$50.00
    2Claude Opus 588.4%$5.00$25.00
    3Kimi K385.0%$3.00$15.00
    4Claude Opus 4.882.7%$5.00$25.00
    5DeepSeek-V4-Pro-081382.3%$1.32$3.96
    6Claude Sonnet 581.3%$2.00$10.00
    7GPT-5.6 Sol80.5%$5.00$30.00
    8Muse Spark 1.279.1%$1.25$4.25

    Related LLM leaderboards

    LLM LeaderboardCodingMathAgenticReasoningWritingScienceFinanceLong ContextVisionOpen Source

    Individual benchmark pages

    Rank one eval at a time. All LLM benchmarks.

    HLESWE BenchHumanity's Last Exam (No Tools)Humanity's Last Exam (With Tools)Terminal-Bench 2.0Terminal-BenchTerminal-Bench 2.1Terminal-Bench 2Terminal-Bench 3.0ARC-AGI-1 Verified

    Vibe Code Bench FAQ

    Who ranks #1 on the Vibe Code Bench leaderboard?

    As of August 20, 2026, Claude Fable 5 by Anthropic ranks #1 on Vibe Code Bench at 90.3%. API pricing is $10.00/M input and $50.00/M output.

    What are the top models on Vibe Code Bench?

    The current Vibe Code Bench ranking as of August 20, 2026 is 1. Claude Fable 5 at 90.3%; 2. Claude Opus 5 at 88.4%; 3. Kimi K3 at 85.0%.

    Which vibe code bench model is the cheapest?

    MiMo-V2.5 is the cheapest scored model on this vibe code bench leaderboard at $0.17/M input and $0.34/M output ($0.50 blended). Claude Fable 5 still leads Vibe Code Bench at 90.3%.

    Should I always pick the #1 Vibe Code Bench model?

    Not automatically. Claude Fable 5 leads Vibe Code Bench, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh Vibe Code Bench against input/output price, context window, and related evals.

    How often is the Vibe Code Bench leaderboard updated?

    Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 20, 2026. Treat it as a current index, not a one-off blog post.

    What is Vibe Code Bench?

    Vibe Code Bench — Vals.ai coding eval for realistic product-style implementation quality, not just unit-test patches. This page ranks models that have published a Vibe Code Bench score, with live API token prices on the same row.

    Where is the Vibe Code Bench leaderboard?

    This page is the Vibe Code Bench leaderboard. Models are sorted by Vibe Code Bench, with input and output token prices on the same row so you can weigh score against cost. Official boards often omit price; that comparison is the point of this index.

    How is this Vibe Code Bench ranking different from the official board?

    Official eval pages own the methodology. This page keeps the published Vibe Code Bench score next to live API $/M so you can pick a production SKU, not only a trophy number.