AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    SciCode

    🏆 Leaderboard

    As of August 20, 2026, Claude Fable 5 is #1 for SciCode at 60.2%. Ranked by the SciCode score 90 models in this index have a published SciCode score. SciCode leaderboard with live API prices. SciCode — scientific coding and research-programming benchmark.

    Updated August 20, 2026282 models33 providers
    Claude Fable 5
    Anthropic · Proprietary
    		60.2%$60.00
    Gemini 3.1 Pro
    Google · Proprietary
    		59%$17.50
    Kimi K3OSS
    Moonshot AI · Open Source
    		58.7%$18.00
    Muse Spark 1.1
    Meta · Proprietary
    		58.2%$5.50
    Seed 2.1 Turbo
    ByteDance · Proprietary
    		57.8%$3.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		56.9%$35.00
    GPT-5.4
    OpenAI · Proprietary
    		56.6%$17.50
    GPT-5.5
    OpenAI · Proprietary
    		56.1%$35.00
    Claude Opus 5
    Anthropic · Proprietary
    		55.7%$30.00
    Claude Opus 4.7
    Anthropic · Proprietary
    		54.5%$30.00
    Grok 4.5
    xAI · Proprietary
    		54.0%$8.00
    GPT-5.6 Terra
    OpenAI · Proprietary
    		53.9%$14.00
    Claude Sonnet 5
    Anthropic · Proprietary
    		53.6%$12.00
    Qwen3.7 Max
    Qwen · Proprietary
    		53.5%$5.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		53.5%$30.00
    Gemini 3.5 Flash
    Google · Proprietary
    		53.1%$10.50
    Gemini 3.6 Flash
    Google · Proprietary
    		52.7%$4.50
    GPT-5.6 Luna
    OpenAI · Proprietary
    		52.5%$1.40
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		52.2%$4.93
    Qwen3.7-Plus
    Qwen · Proprietary
    		51.3%$1.60
    GLM-5.2OSS
    Z AI · Open Source
    		50.5%$5.80
    MiMo-V2.5-ProOSS
    Xiaomi · Open Source
    		50.2%$1.30
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek · Open Source
    		50%$5.22
    GPT-5.4 mini
    OpenAI · Proprietary
    		49.9%$5.25
    DeepSeek-V4-Flash-0731OSS
    DeepSeek · Open Source
    		49.9%$1.76
    Kimi K2.5OSS
    Moonshot AI · Open Source
    		48.7%$3.68
    Inkling-SmallOSS
    Thinking Machines · Open Source · via Thinking Machines Lab
    		48.7%$1.50
    GPT-5.5 Instant
    OpenAI · Proprietary
    		48.6%$35.00
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		47.5%$4.93
    Grok 4.3
    xAI · Proprietary
    		47.3%$3.75
    MiniMax M2.7OSS
    MiniMax · Open Source
    		47.0%$1.50
    GPT-5.4 nano
    OpenAI · Proprietary
    		46.9%$1.45
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		46.8%$18.00
    MiniMax M3OSS
    MiniMax · Open Source
    		45.4%$1.50
    GLM-4.7OSS
    Z AI · Open Source
    		45.1%$2.80
    DeepSeek-V4-Flash-MaxOSS
    DeepSeek · Open Source
    		44.9%$0.42
    Kimi K2-Thinking-0905OSS
    Moonshot AI · Open Source
    		44.8%$2.47
    Claude Sonnet 4.5
    Anthropic · Proprietary
    		44.7%$18.00
    Nemotron 3 Ultra (550B A55B)OSS
    NVIDIA · Open Source · via OpenRouter
    		44.6%$2.70
    GLM-5.1OSS
    Z AI · Open Source
    		43.8%$5.80
    Muse Glimmer-30BOSS
    Meta · Open Source
    		43.6%$1.85
    Gemma 4 31BOSS
    Google · Open Source
    		43.4%$0.54
    GPT-5.1 High
    OpenAI · Proprietary
    		43.3%$11.25
    GPT-5.1
    OpenAI · Proprietary
    		43.3%$11.25
    Claude Haiku 4.5
    Anthropic · Proprietary
    		43.3%$6.00
    MiMo-V2.5OSS
    Xiaomi · Open Source
    		43.1%$0.50
    GPT-5 High
    OpenAI · Proprietary
    		42.9%$11.25
    GPT-5
    OpenAI · Proprietary
    		42.9%$11.25
    Gemini 2.5 Pro
    Google · Proprietary
    		42.8%$11.25
    Qwen3-235B-A22B-Thinking-2507OSS
    Qwen · Open Source
    		42.4%$3.30
    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 SciCode right now?

    As of August 20, 2026, Claude Fable 5 by Anthropic is #1 for SciCode at 60.2%. Ranked by the SciCode score This board also tracks SciCode. Next on the same board: Gemini 3.1 Pro and Kimi K3. This scicode leaderboard ranks models by SciCode. 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 scicode. Ranked by the SciCode score Input and output are dollars per million tokens.
    RankModelSciCodeInput /MOutput /M
    1Claude Fable 560.2%$10.00$50.00
    2Gemini 3.1 Pro59%$2.50$15.00
    3Kimi K358.7%$3.00$15.00
    4Muse Spark 1.158.2%$1.25$4.25
    5Seed 2.1 Turbo57.8%$0.50$2.50
    6GPT-5.6 Sol56.9%$5.00$30.00
    7GPT-5.456.6%$2.50$15.00
    8GPT-5.556.1%$5.00$30.00

    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

    SciCode FAQ

    Who ranks #1 on the SciCode leaderboard?

    As of August 20, 2026, Claude Fable 5 by Anthropic ranks #1 on SciCode at 60.2%. API pricing is $10.00/M input and $50.00/M output.

    What are the top models on SciCode?

    The current SciCode ranking as of August 20, 2026 is 1. Claude Fable 5 at 60.2%; 2. Gemini 3.1 Pro at 59%; 3. Kimi K3 at 58.7%.

    Which scicode model is the cheapest?

    Llama 3.1 8B Instruct is the cheapest scored model on this scicode leaderboard at $0.03/M input and $0.03/M output ($0.06 blended). Claude Fable 5 still leads SciCode at 60.2%.

    Should I always pick the #1 SciCode model?

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

    How often is the SciCode 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 SciCode?

    SciCode — scientific coding and research-programming benchmark. This page ranks models that have published a SciCode score, with live API token prices on the same row.

    Where is the SciCode leaderboard?

    This page is the SciCode leaderboard. Models are sorted by SciCode, 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 SciCode ranking different from the official board?

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