AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    ProofBench

    🏆 Leaderboard

    As of August 20, 2026, Claude Opus 5 is #1 for ProofBench at 78%. Ranked by the ProofBench score 52 models in this index have a published ProofBench score. ProofBench leaderboard: rank models by ProofBench next to live API token prices.

    Updated August 20, 2026282 models33 providers
    Claude Opus 5
    Anthropic · Proprietary
    		78%$30.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		77%$35.00
    Claude Fable 5
    Anthropic · Proprietary
    		77%$60.00
    GPT-5.6 Terra
    OpenAI · Proprietary
    		71%$14.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		70%$18.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		69%$30.00
    Claude Sonnet 5
    Anthropic · Proprietary
    		66%$12.00
    Qwen3.8 MaxOSS
    Qwen · Open Source
    		58%$8.00
    Gemini 3.7 Flash
    Google · Proprietary
    		58%$4.50
    GPT-5.4
    OpenAI · Proprietary
    		56%$17.50
    DeepSeek-V4-Flash-0731OSS
    DeepSeek · Open Source
    		56%$1.76
    GPT-5.6 Luna
    OpenAI · Proprietary
    		54%$1.40
    Claude Opus 4.7
    Anthropic · Proprietary
    		54%$30.00
    Grok 4.6
    xAI · Proprietary
    		51%$8.00
    GPT-5.5
    OpenAI · Proprietary
    		50%$35.00
    DeepSeek-V4-Pro-0813OSS
    DeepSeek · Open Source
    		50%$5.28
    Claude Opus 4.6
    Anthropic · Proprietary
    		50%$30.00
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		45%$18.00
    Muse Spark 1.2
    Meta · Proprietary
    		43%$5.50
    Muse Spark 1.1
    Meta · Proprietary
    		39%$5.50
    Gemini 3.6 Flash
    Google · Proprietary
    		36%$4.50
    Claude Opus 4.5
    Anthropic · Proprietary
    		36%$30.00
    GLM-5.2OSS
    Z AI · Open Source
    		35%$5.80
    Grok 4.5
    xAI · Proprietary
    		30%$8.00
    Gemini 3.5 Flash
    Google · Proprietary
    		29%$10.50
    Qwen3.7 Max
    Qwen · Proprietary
    		26%$5.00
    Gemini 3.1 Pro
    Google · Proprietary
    		26%$17.50
    MiMo-V2.5-ProOSS
    Xiaomi · Open Source
    		24%$1.30
    GLM-5.1OSS
    Z AI · Open Source
    		22.2%$5.80
    GPT-5.4 mini
    OpenAI · Proprietary
    		21%$5.25
    Gemini 3 Pro
    Google · Proprietary
    		20%$14.00
    MiniMax M3OSS
    MiniMax · Open Source
    		19%$1.50
    Claude Sonnet 4.5
    Anthropic · Proprietary
    		19%$18.00
    GPT-5
    OpenAI · Proprietary
    		18%$11.25
    MiMo-V2.5OSS
    Xiaomi · Open Source
    		16%$0.50
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		16%$4.93
    GPT-5.2
    OpenAI · Proprietary
    		15%$15.75
    Gemini 3 Flash
    Google · Proprietary
    		15%$3.50
    Gemini 3.5 Flash-Lite
    Google · Proprietary
    		13%$2.80
    GPT-5 nano
    OpenAI · Proprietary
    		12%$0.45
    Grok 4.3
    xAI · Proprietary
    		11%$3.75
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek · Open Source
    		10%$5.22
    Mistral Medium 3.5OSS
    Mistral · Open Source · via Mistral AI
    		9%$9.00
    GPT-5.1 Codex
    OpenAI · Proprietary
    		9%$11.25
    GPT-5 mini
    OpenAI · Proprietary
    		9%$2.25
    GLM-4.7OSS
    Z AI · Open Source
    		6%$2.80
    Inkling-SmallOSS
    Thinking Machines · Open Source · via Thinking Machines Lab
    		5%$1.50
    GPT-5.4 nano
    OpenAI · Proprietary
    		5%$1.45
    MiniMax M2.5OSS
    MiniMax · Open Source
    		4%$1.50
    Grok-4.1 Fast Reasoning
    xAI · Proprietary
    		4%$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.

    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 ProofBench right now?

    As of August 20, 2026, Claude Opus 5 by Anthropic is #1 for ProofBench at 78%. Ranked by the ProofBench score This board also tracks ProofBench. Next on the same board: GPT-5.6 Sol and Claude Fable 5. This proofbench leaderboard ranks models by ProofBench. 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 proofbench. Ranked by the ProofBench score Input and output are dollars per million tokens.
    RankModelProofBenchInput /MOutput /M
    1Claude Opus 578%$5.00$25.00
    2GPT-5.6 Sol77%$5.00$30.00
    3Claude Fable 577%$10.00$50.00
    4GPT-5.6 Terra71%$2.00$12.00
    5Kimi K370%$3.00$15.00
    6Claude Opus 4.869%$5.00$25.00
    7Claude Sonnet 566%$2.00$10.00
    8Gemini 3.7 Flash58%$0.75$3.75

    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

    ProofBench FAQ

    Who ranks #1 on the ProofBench leaderboard?

    As of August 20, 2026, Claude Opus 5 by Anthropic ranks #1 on ProofBench at 78%. API pricing is $5.00/M input and $25.00/M output.

    What are the top models on ProofBench?

    The current ProofBench ranking as of August 20, 2026 is 1. Claude Opus 5 at 78%; 2. GPT-5.6 Sol at 77%; 3. Claude Fable 5 at 77%.

    Which proofbench model is the cheapest?

    GPT-5 nano is the cheapest scored model on this proofbench leaderboard at $0.05/M input and $0.40/M output ($0.45 blended). Claude Opus 5 still leads ProofBench at 78%.

    Should I always pick the #1 ProofBench model?

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

    How often is the ProofBench 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 ProofBench?

    ProofBench is a public LLM eval (the ProofBench score). This page ranks models that have published a score, next to live API prices.

    Where is the ProofBench leaderboard?

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

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