AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    APEX-Agents

    🏆 Leaderboard

    As of August 31, 2026, Grok 4.6 is #1 for APEX-Agents at 57.5%. Ranked by the APEX-Agents score 51 models in this index have a published APEX-Agents score. APEX-Agents leaderboard with live API prices. APEX-Agents — agent execution benchmark across professional workflows.

    Updated August 31, 2026345 models36 providers

    APEX-Agents vs price

    51 models. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price — a dot under it is a worse deal than something on the line.

    Best score at each price#1 on this board
    Grok 4.6
    xAI · Proprietary
    		57.5%$8.00
    Claude Fable 5
    Anthropic · Proprietary
    		45%$60.00
    Claude Opus 5
    Anthropic · Proprietary
    		43.5%$30.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		42.5%$30.00
    Muse Spark 1.1
    Meta · Proprietary
    		41.9%$5.50
    GPT-5.6 Sol
    OpenAI · Proprietary
    		39.9%$35.00
    GPT-5.5
    OpenAI · Proprietary
    		38.5%$35.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		37.6%$18.00
    GPT-5.4
    OpenAI · Proprietary
    		36%$17.50
    GLM-5.2OSS
    Z AI · Open Source
    		35.6%$5.80
    GPT-5.2
    OpenAI · Proprietary
    		34.4%$15.75
    Grok 4.5
    xAI · Proprietary
    		34.2%$8.00
    Claude Opus 4.7
    Anthropic · Proprietary
    		33.9%$30.00
    Seed 2.1 Pro
    ByteDance · Proprietary
    		33.8%$5.34
    Gemini 3.1 Pro
    Google · Proprietary
    		33.5%$17.50
    Claude Sonnet 5
    Anthropic · Proprietary
    		32.5%$12.00
    Claude Opus 4.6
    Anthropic · Proprietary
    		32.4%$30.00
    GPT-5.3 Codex
    OpenAI · Proprietary
    		31.8%$15.75
    Gemini 3 Pro
    Google · Proprietary
    		31.5%$14.00
    Seed 2.1 Turbo
    ByteDance · Proprietary
    		29.2%$3.00
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		27.9%$4.93
    MiniMax M3OSS
    MiniMax · Open Source
    		27.7%$1.50
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		27.6%$4.93
    GPT-5.2 Codex
    OpenAI · Proprietary
    		27.6%$15.75
    Hy3OSS
    Tencent · Open Source
    		25.6%$0.66
    GPT-5.4 mini
    OpenAI · Proprietary
    		24.6%$5.25
    Gemini 3 Flash
    Google · Proprietary
    		24%$3.50
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		23.7%$18.00
    GPT-5.1 Codex
    OpenAI · Proprietary
    		20.7%$11.25
    Claude Opus 4.5
    Anthropic · Proprietary
    		20.7%$30.00
    GPT-5 Codex
    OpenAI · Proprietary
    		20.1%$11.25
    GPT-5
    OpenAI · Proprietary
    		18.3%$11.25
    GPT-5.1
    OpenAI · Proprietary
    		17.5%$11.25
    o3
    OpenAI · Proprietary
    		17.2%$10.00
    GLM-5OSS
    Z AI · Open Source
    		17.2%$4.20
    GPT-5.4 nano
    OpenAI · Proprietary
    		16.9%$1.45
    Grok-4
    xAI · Proprietary
    		15.2%$18.00
    Kimi K2.5OSS
    Moonshot AI · Open Source
    		14.4%$3.68
    Gemini 3.1 Flash-Lite
    Google · Proprietary
    		13%$1.75
    Grok-4.1
    xAI · Proprietary
    		12.8%$18.00
    Claude Sonnet 4
    Anthropic · Proprietary
    		9.3%$18.00
    Claude Haiku 4.5
    Anthropic · Proprietary
    		8.9%$6.00
    GLM-4.7OSS
    Z AI · Open Source
    		8.7%$2.80
    DeepSeek-V3.2OSS
    DeepSeek · Open Source · via OpenRouter
    		7%$0.57
    Gemini 2.5 Pro
    Google · Proprietary
    		6.6%$11.25
    MiniMax M2.5OSS
    MiniMax · Open Source
    		6.2%$1.50
    GPT OSS 120BOSS
    OpenAI · Open Source
    		4.7%$0.54
    GLM-4.6OSS
    Z AI · Open Source
    		4%$2.80
    Grok-3
    xAI · Proprietary
    		2.1%$18.00
    Gemini 2.5 Flash
    Google · Proprietary
    		1.8%$2.80
    Showing 1–50 of 345 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

    345 models across 36 providers. Search or jump to a lab — every model page stays linked here.

    OpenAI52Anthropic22Google34Cursor2xAI17DeepSeek20MiniMax7Qwen55AI21 Labs2Amazon7Baidu2ByteDance4Cohere4IBM2Inception1inclusionAI1LG AI Research1Liquid AI2Meituan4Meta12Microsoft9Mistral26Moonshot AI11Nous Research1NVIDIA9OpenBMB1Poolside2Sakana AI1Sarvam AI2StepFun2Tencent1Thinking Machines1Unisound1Upstage1Xiaomi5Z AI21

    Baidu

    2 models
    ERNIE 5.0ERNIE 4.5

    Inception

    1 models
    Mercury 2

    inclusionAI

    1 models
    Ling-3.0-flash

    LG AI Research

    1 models
    K-EXAONE-236B-A23B

    Liquid AI

    2 models
    LFM2.5-VL-3BLFM2.5-2.6B

    Nous Research

    1 models
    Hermes 3 70B

    OpenBMB

    1 models
    MiniCPM-SALA

    Sakana AI

    1 models
    Sakana Namazu

    Sarvam AI

    2 models
    Sarvam-105BSarvam-30B

    Tencent

    1 models
    Hy3

    Thinking Machines

    1 models
    Inkling-Small

    Unisound

    1 models
    U2

    Upstage

    1 models
    Solar Pro 4

    Which model leads APEX-Agents right now?

    As of August 31, 2026, Grok 4.6 by xAI is #1 for APEX-Agents at 57.5%. Ranked by the APEX-Agents score This board also tracks APEX-Agents. Next on the same board: Claude Fable 5 and Claude Opus 5. This apex-agents leaderboard ranks models by APEX-Agents. 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 apex-agents. Ranked by the APEX-Agents score Input and output are dollars per million tokens.
    RankModelAPEX-AgentsInput /MOutput /M
    1Grok 4.657.5%$2.00$6.00
    2Claude Fable 545%$10.00$50.00
    3Claude Opus 543.5%$5.00$25.00
    4Claude Opus 4.842.5%$5.00$25.00
    5Muse Spark 1.141.9%$1.25$4.25
    6GPT-5.6 Sol39.9%$5.00$30.00
    7GPT-5.538.5%$5.00$30.00
    8Kimi K337.6%$3.00$15.00

    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

    APEX-Agents FAQ

    Who ranks #1 on the APEX-Agents leaderboard?

    As of August 31, 2026, Grok 4.6 by xAI ranks #1 on APEX-Agents at 57.5%. API pricing is $2.00/M input and $6.00/M output.

    What are the top models on APEX-Agents?

    The current APEX-Agents ranking as of August 31, 2026 is 1. Grok 4.6 at 57.5%; 2. Claude Fable 5 at 45%; 3. Claude Opus 5 at 43.5%.

    Which apex-agents model is the cheapest?

    GPT OSS 120B is the cheapest scored model on this apex-agents leaderboard at $0.09/M input and $0.45/M output ($0.54 blended). Grok 4.6 still leads APEX-Agents at 57.5%.

    Should I always pick the #1 APEX-Agents model?

    Not automatically. Grok 4.6 leads APEX-Agents, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh APEX-Agents against input/output price, context window, and related evals.

    How often is the APEX-Agents leaderboard updated?

    Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 31, 2026. Treat it as a current index, not a one-off blog post.

    What is APEX-Agents?

    APEX-Agents — agent execution benchmark across professional workflows. This page ranks models that have published a APEX-Agents score, with live API token prices on the same row.

    Where is the APEX-Agents leaderboard?

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

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