AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    DeepSWE

    🏆 Leaderboard

    As of August 20, 2026, Claude Opus 5 is #1 for DeepSWE at 73.7%. Ranked by DeepSWE: repository-level coding agents on real GitHub work. 34 models in this index have a published DeepSWE score. DeepSWE leaderboard with live API prices. DeepSWE — software engineering agent benchmark on real repositories.

    Updated August 20, 2026282 models33 providers
    Claude Opus 5
    Anthropic · Proprietary
    		73.7%$30.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		72.7%$35.00
    GPT-5.5
    OpenAI · Proprietary
    		70.0%$35.00
    Claude Fable 5
    Anthropic · Proprietary
    		69.9%$60.00
    GPT-5.6 Terra
    OpenAI · Proprietary
    		69.6%$14.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		67.5%$18.00
    GPT-5.6 Luna
    OpenAI · Proprietary
    		67.2%$1.40
    DeepSeek-V4-Pro-0813OSS
    DeepSeek · Open Source
    		62.7%$5.28
    Claude Opus 4.8
    Anthropic · Proprietary
    		58.2%$30.00
    GPT-5.4
    OpenAI · Proprietary
    		55.5%$17.50
    DeepSeek-V4-Flash-0731OSS
    DeepSeek · Open Source
    		54.4%$1.76
    Claude Opus 4.7
    Anthropic · Proprietary
    		54.2%$30.00
    Claude Sonnet 5
    Anthropic · Proprietary
    		53.9%$12.00
    Muse Spark 1.1
    Meta · Proprietary
    		53.3%$5.50
    Grok 4.5
    xAI · Proprietary
    		53%$8.00
    Gemini 3.6 Flash
    Google · Proprietary
    		48.6%$4.50
    GLM-5.2OSS
    Z AI · Open Source
    		41.5%$5.80
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		31.8%$18.00
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		30.5%$4.93
    Gemini 3.5 Flash
    Google · Proprietary
    		28.3%$10.50
    Hy3OSS
    Tencent · Open Source
    		28%$0.66
    Claude Opus 4.6
    Anthropic · Proprietary
    		27.6%$30.00
    GPT-5.4 mini
    OpenAI · Proprietary
    		24.3%$5.25
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		23.9%$4.93
    Seed 2.1 Turbo
    ByteDance · Proprietary
    		23%$3.00
    MiniMax M3OSS
    MiniMax · Open Source
    		20.4%$1.50
    MiMo-V2.5-ProOSS
    Xiaomi · Open Source
    		19.5%$1.30
    Qwen3.7 Max
    Qwen · Proprietary
    		17.7%$5.00
    GLM-5.1OSS
    Z AI · Open Source
    		17.5%$5.80
    Gemini 3.1 Pro
    Google · Proprietary
    		9.7%$17.50
    Gemini 3 Flash
    Google · Proprietary
    		5.1%$3.50
    Qwen3.6 Plus
    Qwen · Proprietary
    		2.6%$3.50
    MiniMax M2.7OSS
    MiniMax · Open Source
    		0.2%$1.50
    Claude Haiku 4.5
    Anthropic · Proprietary
    		0.2%$6.00
    ChatGPT-4o Latest
    OpenAI · Proprietary
    		—$12.50
    Claude 3 Haiku
    Anthropic · Proprietary
    		—$1.50
    Claude 3 Opus
    Anthropic · Proprietary
    		—$90.00
    Claude 3 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.5 Haiku
    Anthropic · Proprietary
    		—$4.80
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude 3.7 Sonnet
    Anthropic · Proprietary
    		—$18.00
    Claude Mythos 5
    Anthropic · Proprietary
    		—$60.00
    Claude Mythos Preview
    Anthropic · Proprietary
    		—$60.00
    Claude Opus 4
    Anthropic · Proprietary
    		—$90.00
    Claude Opus 4.1
    Anthropic · Proprietary
    		—$90.00
    Claude Opus 4.5
    Anthropic · Proprietary
    		—$30.00
    Claude Sonnet 4
    Anthropic · Proprietary
    		—$18.00
    Claude Sonnet 4.5
    Anthropic · Proprietary
    		—$18.00
    Command A+OSS
    Cohere · Open Source
    		—$12.50
    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 DeepSWE right now?

    As of August 20, 2026, Claude Opus 5 by Anthropic is #1 for DeepSWE at 73.7%. Ranked by DeepSWE: repository-level coding agents on real GitHub work. This board also tracks DeepSWE. Next on the same board: GPT-5.6 Sol and GPT-5.5. This deepswe leaderboard ranks models by DeepSWE. 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 deepswe. Ranked by DeepSWE: repository-level coding agents on real GitHub work. Input and output are dollars per million tokens.
    RankModelDeepSWEInput /MOutput /M
    1Claude Opus 573.7%$5.00$25.00
    2GPT-5.6 Sol72.7%$5.00$30.00
    3GPT-5.570.0%$5.00$30.00
    4Claude Fable 569.9%$10.00$50.00
    5GPT-5.6 Terra69.6%$2.00$12.00
    6Kimi K367.5%$3.00$15.00
    7GPT-5.6 Luna67.2%$0.20$1.20
    8DeepSeek-V4-Pro-081362.7%$1.32$3.96

    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

    DeepSWE FAQ

    Who ranks #1 on the DeepSWE leaderboard?

    As of August 20, 2026, Claude Opus 5 by Anthropic ranks #1 on DeepSWE at 73.7%. API pricing is $5.00/M input and $25.00/M output.

    What are the top models on DeepSWE?

    The current DeepSWE ranking as of August 20, 2026 is 1. Claude Opus 5 at 73.7%; 2. GPT-5.6 Sol at 72.7%; 3. GPT-5.5 at 70.0%.

    Which deepswe model is the cheapest?

    Hy3 is the cheapest scored model on this deepswe leaderboard at $0.13/M input and $0.53/M output ($0.66 blended). Claude Opus 5 still leads DeepSWE at 73.7%.

    Should I always pick the #1 DeepSWE model?

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

    How often is the DeepSWE 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 DeepSWE?

    DeepSWE — software engineering agent benchmark on real repositories. This page ranks models that have published a DeepSWE score, with live API token prices on the same row.

    Where is the DeepSWE leaderboard?

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

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