AnotherWrapper
    $249
    LLMImageVideoSpeechTranscription

    SAGE

    🏆 Leaderboard

    As of August 20, 2026, Claude Opus 4.7 is #1 for SAGE at 56.1%. Ranked by the SAGE score 55 models in this index have a published SAGE score. SAGE leaderboard with live API prices. SAGE — Vals.ai safety and generalized evaluation suite.

    Updated August 20, 2026282 models33 providers
    Claude Opus 4.7
    Anthropic · Proprietary
    		56.1%$30.00
    Gemma 4 31BOSS
    Google · Open Source
    		55.0%$0.54
    Claude Opus 4.8
    Anthropic · Proprietary
    		54.8%$30.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		54.3%$18.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		52.6%$35.00
    Claude Fable 5
    Anthropic · Proprietary
    		51.9%$60.00
    Gemini 3 Flash
    Google · Proprietary
    		51.9%$3.50
    GPT-5.5
    OpenAI · Proprietary
    		51.5%$35.00
    Qwen3.8 MaxOSS
    Qwen · Open Source
    		51.3%$8.00
    GPT-5.4 mini
    OpenAI · Proprietary
    		50.8%$5.25
    MiniMax M3OSS
    MiniMax · Open Source
    		50.6%$1.50
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		50.2%$4.93
    Gemini 3.5 Flash
    Google · Proprietary
    		49.9%$10.50
    Gemini 3.1 Flash-Lite
    Google · Proprietary
    		49.5%$1.75
    Claude Opus 5
    Anthropic · Proprietary
    		49.4%$30.00
    GPT-5.2
    OpenAI · Proprietary
    		49.3%$15.75
    Gemini 3.7 Flash
    Google · Proprietary
    		49.2%$4.50
    Claude Sonnet 5
    Anthropic · Proprietary
    		48.9%$12.00
    Gemini 3.6 Flash
    Google · Proprietary
    		48.7%$4.50
    Gemini 3.1 Pro
    Google · Proprietary
    		48.7%$17.50
    Muse Spark 1.2
    Meta · Proprietary
    		47.7%$5.50
    Gemini 3 Pro
    Google · Proprietary
    		47.6%$14.00
    Gemini 3.5 Flash-Lite
    Google · Proprietary
    		47.3%$2.80
    GPT-5.6 Terra
    OpenAI · Proprietary
    		47%$14.00
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		46.6%$18.00
    Qwen3.6-27BOSS
    Qwen · Open Source
    		45.6%$4.20
    Muse Spark 1.1
    Meta · Proprietary
    		45.6%$5.50
    Claude Opus 4.5
    Anthropic · Proprietary
    		45%$30.00
    Qwen3.6 Plus
    Qwen · Proprietary
    		44.9%$3.50
    Gemini 2.5 Flash
    Google · Proprietary
    		44.8%$2.80
    GPT-5.6 Luna
    OpenAI · Proprietary
    		44.2%$1.40
    GPT-5
    OpenAI · Proprietary
    		43.7%$11.25
    GPT-5.4
    OpenAI · Proprietary
    		43.3%$17.50
    MiMo-V2.5OSS
    Xiaomi · Open Source
    		43.3%$0.50
    GPT-5.1
    OpenAI · Proprietary
    		43.2%$11.25
    GPT-5 mini
    OpenAI · Proprietary
    		43.0%$2.25
    Gemini 2.5 Pro
    Google · Proprietary
    		41.9%$11.25
    o3
    OpenAI · Proprietary
    		41.8%$10.00
    o4-mini
    OpenAI · Proprietary
    		41.1%$5.50
    Qwen3.7-Plus
    Qwen · Proprietary
    		39.3%$1.60
    GPT-5.4 nano
    OpenAI · Proprietary
    		38.1%$1.45
    Mistral Medium 3.5OSS
    Mistral · Open Source · via Mistral AI
    		37.6%$9.00
    Claude Sonnet 4
    Anthropic · Proprietary
    		35%$18.00
    Grok 4.5
    xAI · Proprietary
    		35.0%$8.00
    Claude Sonnet 4.5
    Anthropic · Proprietary
    		32.9%$18.00
    Inkling-SmallOSS
    Thinking Machines · Open Source · via Thinking Machines Lab
    		32.7%$1.50
    Claude Opus 4.1
    Anthropic · Proprietary
    		31.4%$90.00
    Grok-4.1 Fast Reasoning
    xAI · Proprietary
    		31.3%$0.70
    GPT-5 nano
    OpenAI · Proprietary
    		30.4%$0.45
    Grok-4 Fast Reasoning
    xAI · Proprietary
    		29.8%$0.70
    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.

    Get the stack — $249Have 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 SAGE right now?

    As of August 20, 2026, Claude Opus 4.7 by Anthropic is #1 for SAGE at 56.1%. Ranked by the SAGE score This board also tracks SAGE. Next on the same board: Gemma 4 31B and Claude Opus 4.8. This sage leaderboard ranks models by SAGE. 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 sage. Ranked by the SAGE score Input and output are dollars per million tokens.
    RankModelSAGEInput /MOutput /M
    1Claude Opus 4.756.1%$5.00$25.00
    2Gemma 4 31B55.0%$0.14$0.40
    3Claude Opus 4.854.8%$5.00$25.00
    4Kimi K354.3%$3.00$15.00
    5GPT-5.6 Sol52.6%$5.00$30.00
    6Claude Fable 551.9%$10.00$50.00
    7Gemini 3 Flash51.9%$0.50$3.00
    8GPT-5.551.5%$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

    SAGE FAQ

    Who ranks #1 on the SAGE leaderboard?

    As of August 20, 2026, Claude Opus 4.7 by Anthropic ranks #1 on SAGE at 56.1%. API pricing is $5.00/M input and $25.00/M output.

    What are the top models on SAGE?

    The current SAGE ranking as of August 20, 2026 is 1. Claude Opus 4.7 at 56.1%; 2. Gemma 4 31B at 55.0%; 3. Claude Opus 4.8 at 54.8%.

    Which sage model is the cheapest?

    GPT-5 nano is the cheapest scored model on this sage leaderboard at $0.05/M input and $0.40/M output ($0.45 blended). Claude Opus 4.7 still leads SAGE at 56.1%.

    Should I always pick the #1 SAGE model?

    Not automatically. Claude Opus 4.7 leads SAGE, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh SAGE against input/output price, context window, and related evals.

    How often is the SAGE 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 SAGE?

    SAGE — Vals.ai safety and generalized evaluation suite. This page ranks models that have published a SAGE score, with live API token prices on the same row.

    Where is the SAGE leaderboard?

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

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