AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    LiveBench

    🏆 Leaderboard

    As of August 20, 2026, o3-mini is #1 for LiveBench at 84.6%. Ranked by the LiveBench score 55 models in this index have a published LiveBench score. LiveBench leaderboard: rank models by LiveBench next to live API token prices.

    Updated August 20, 2026282 models33 providers
    o3-mini
    OpenAI · Proprietary
    		84.6%$5.50
    GPT-5.5
    OpenAI · Proprietary
    		80.7%$35.00
    GPT-5.4
    OpenAI · Proprietary
    		80.3%$17.50
    Gemini 3.1 Pro
    Google · Proprietary
    		79.9%$17.50
    GPT-5.1
    OpenAI · Proprietary
    		78.8%$11.25
    Claude Fable 5
    Anthropic · Proprietary
    		78.3%$60.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		77.2%$30.00
    Qwen3 235B A22BOSS
    Qwen · Open Source
    		77.1%$0.20
    Claude Opus 4.7
    Anthropic · Proprietary
    		76.9%$30.00
    Kimi K2-Instruct-0905OSS
    Moonshot AI · Open Source · via OpenRouter
    		76.4%$3.10
    Kimi K2 InstructOSS
    Moonshot AI · Open Source
    		76.4%$1.00
    Claude Opus 4.6
    Anthropic · Proprietary
    		76.3%$30.00
    Claude 3.7 Sonnet
    Anthropic · Proprietary
    		76.1%$18.00
    Claude Opus 4.5
    Anthropic · Proprietary
    		76.0%$30.00
    Claude Sonnet 4.6
    Anthropic · Proprietary
    		75.5%$18.00
    Gemini 3.5 Flash
    Google · Proprietary
    		75.0%$10.50
    Qwen3 32BOSS
    Qwen · Open Source
    		74.9%$0.54
    GPT-5.2
    OpenAI · Proprietary
    		74.8%$15.75
    Qwen3 30B A3BOSS
    Qwen · Open Source
    		74.3%$0.54
    GPT-5.2 Codex
    OpenAI · Proprietary
    		74.3%$15.75
    Qwen3.7 Max
    Qwen · Proprietary
    		74.3%$5.00
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek · Open Source
    		73.6%$5.22
    Gemini 3 Pro
    Google · Proprietary
    		73.4%$14.00
    GPT-5.3 Codex
    OpenAI · Proprietary
    		72.8%$15.75
    Gemini 3 Flash
    Google · Proprietary
    		72.4%$3.50
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		72.2%$4.93
    GPT-5.1 High
    OpenAI · Proprietary
    		72.0%$11.25
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		71.9%$4.93
    DeepSeek-R1OSS
    DeepSeek · Open Source
    		71.6%$2.74
    Qwen3.6 Plus
    Qwen · Proprietary
    		70.8%$3.50
    GLM-5.1OSS
    Z AI · Open Source
    		70.2%$5.80
    GPT-5.4 nano
    OpenAI · Proprietary
    		70.1%$1.45
    MiniMax M3OSS
    MiniMax · Open Source
    		70.0%$1.50
    Kimi K2.5OSS
    Moonshot AI · Open Source
    		69.1%$3.68
    o1
    OpenAI · Proprietary
    		67%$75.00
    DeepSeek-V3 0324OSS
    DeepSeek · Open Source
    		66.9%$1.42
    DeepSeek-V3OSS
    DeepSeek · Open Source
    		60.5%$1.37
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		59.0%$18.00
    o1-mini
    OpenAI · Proprietary
    		57.8%$15.00
    GPT-4o
    OpenAI · Proprietary
    		55.3%$12.50
    DeepSeek R1 Distill Llama 70BOSS
    DeepSeek · Open Source
    		54.5%$0.50
    Gemini 2.0 Flash-Lite
    Google · Proprietary
    		54.3%$0.37
    Qwen2.5 72B InstructOSS
    Qwen · Open Source
    		52.3%$0.75
    o1-preview
    OpenAI · Proprietary
    		52.3%$75.00
    Llama 3.3 70B InstructOSS
    Meta · Open Source
    		50.2%$0.40
    Gemma 3 27BOSS
    Google · Open Source
    		50.0%$0.30
    Claude 3 Opus
    Anthropic · Proprietary
    		49.2%$90.00
    Phi 4OSS
    Microsoft · Open Source
    		47.6%$0.21
    Qwen2.5-Coder 32B InstructOSS
    Qwen · Open Source
    		46.2%$0.18
    DeepSeek R1 Distill Qwen 32BOSS
    DeepSeek · Open Source
    		45.5%$0.30
    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 LiveBench right now?

    As of August 20, 2026, o3-mini by OpenAI is #1 for LiveBench at 84.6%. Ranked by the LiveBench score This board also tracks LiveBench. Next on the same board: GPT-5.5 and GPT-5.4. This livebench leaderboard ranks models by LiveBench. 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 livebench. Ranked by the LiveBench score Input and output are dollars per million tokens.
    RankModelLiveBenchInput /MOutput /M
    1o3-mini84.6%$1.10$4.40
    2GPT-5.580.7%$5.00$30.00
    3GPT-5.480.3%$2.50$15.00
    4Gemini 3.1 Pro79.9%$2.50$15.00
    5GPT-5.178.8%$1.25$10.00
    6Claude Fable 578.3%$10.00$50.00
    7Claude Opus 4.877.2%$5.00$25.00
    8Qwen3 235B A22B77.1%$0.10$0.10

    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

    LiveBench FAQ

    Who ranks #1 on the LiveBench leaderboard?

    As of August 20, 2026, o3-mini by OpenAI ranks #1 on LiveBench at 84.6%. API pricing is $1.10/M input and $4.40/M output.

    What are the top models on LiveBench?

    The current LiveBench ranking as of August 20, 2026 is 1. o3-mini at 84.6%; 2. GPT-5.5 at 80.7%; 3. GPT-5.4 at 80.3%.

    Which livebench model is the cheapest?

    Qwen2.5-Coder 32B Instruct is the cheapest scored model on this livebench leaderboard at $0.09/M input and $0.09/M output ($0.18 blended). o3-mini still leads LiveBench at 84.6%.

    Should I always pick the #1 LiveBench model?

    Not automatically. o3-mini leads LiveBench, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh LiveBench against input/output price, context window, and related evals.

    How often is the LiveBench 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 LiveBench?

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

    Where is the LiveBench leaderboard?

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

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