AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    SimpleQA

    🏆 Leaderboard

    As of August 20, 2026, DeepSeek-V3.2-Exp is #1 for SimpleQA at 97.1%. Ranked by SimpleQA, which checks whether the model makes up facts. 86 models in this index have a published SimpleQA score. Methodology: SimpleQA (OpenAI) (https://openai.com/index/introducing-simpleqa/). SimpleQA leaderboard with live API prices. SimpleQA — tests factual accuracy on straightforward questions, measuring hallucination rates. Official methodology: SimpleQA (OpenAI) (https://openai.com/index/introducing-simpleqa/).

    Updated August 20, 2026282 models33 providers
    DeepSeek-V3.2-ExpOSS
    DeepSeek · Open Source
    		97.1%$0.68
    Grok 4 Fast
    xAI · Proprietary
    		95%$0.70
    DeepSeek-V3.1OSS
    DeepSeek · Open Source
    		93.4%$1.27
    DeepSeek-R1-0528OSS
    DeepSeek · Open Source
    		92.3%$2.74
    Gemini 3.1 Pro
    Google · Proprietary
    		77.3%$17.50
    Gemini 3 Pro
    Google · Proprietary
    		72.1%$14.00
    GPT-5.6 Sol
    OpenAI · Proprietary
    		71.6%$35.00
    Gemini 3.7 Flash
    Google · Proprietary
    		71.2%$4.50
    Gemini 3.6 Flash
    Google · Proprietary
    		68.7%$4.50
    Gemini 3 Flash
    Google · Proprietary
    		68.7%$3.50
    Gemini 3.5 Flash
    Google · Proprietary
    		68.4%$10.50
    Claude Fable 5
    Anthropic · Proprietary
    		68.3%$60.00
    Qwen3 Max
    Qwen · Proprietary
    		67.5%$5.50
    Qwen3.7 Max
    Qwen · Proprietary
    		58.5%$5.00
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek · Open Source
    		57.9%$5.22
    Claude Opus 5
    Anthropic · Proprietary
    		56.7%$30.00
    Grok 4.6
    xAI · Proprietary
    		54.4%$8.00
    Qwen3-235B-A22B-Instruct-2507OSS
    Qwen · Open Source
    		54.3%$0.95
    Gemini 2.5 Pro Preview 06-05
    Google · Proprietary
    		54%$11.25
    Grok 4.5
    xAI · Proprietary
    		53.5%$8.00
    o3
    OpenAI · Proprietary
    		53%$10.00
    Qwen3 VL 235B A22B InstructOSS
    Qwen · Open Source
    		51.9%$1.79
    Gemini 2.5 Pro
    Google · Proprietary
    		50.8%$11.25
    GPT-5
    OpenAI · Proprietary
    		50.6%$11.25
    Claude Opus 4.7
    Anthropic · Proprietary
    		50.6%$30.00
    Qwen3-235B-A22B-Thinking-2507OSS
    Qwen · Open Source
    		50.1%$3.30
    Qwen3 VL 8B ThinkingOSS
    Qwen · Open Source
    		49.6%$2.27
    Qwen3.6 Plus
    Qwen · Proprietary
    		49.1%$3.50
    GPT-5.1
    OpenAI · Proprietary
    		48.9%$11.25
    Qwen3 VL 4B InstructOSS
    Qwen · Open Source
    		48%$0.70
    o1
    OpenAI · Proprietary
    		47%$75.00
    Qwen3.8 MaxOSS
    Qwen · Open Source
    		46.3%$8.00
    GPT-5.4
    OpenAI · Proprietary
    		44.8%$17.50
    Qwen3 VL 235B A22B ThinkingOSS
    Qwen · Open Source
    		44.4%$3.94
    Gemini 3.1 Flash-Lite
    Google · Proprietary
    		43.3%$1.75
    GPT-5.6 Terra
    OpenAI · Proprietary
    		43.1%$14.00
    Kimi K3OSS
    Moonshot AI · Open Source
    		42.7%$18.00
    o1-preview
    OpenAI · Proprietary
    		42.4%$75.00
    Claude Opus 4.5
    Anthropic · Proprietary
    		41.8%$30.00
    GPT-5.6 Luna
    OpenAI · Proprietary
    		41.7%$1.40
    Claude Opus 4.6
    Anthropic · Proprietary
    		41.0%$30.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		39.5%$30.00
    Kimi K2.7 CodeOSS
    Moonshot AI · Open Source
    		39.2%$4.93
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		38.7%$4.93
    GPT-4o
    OpenAI · Proprietary
    		38.2%$12.50
    GLM-5.2OSS
    Z AI · Open Source
    		38.1%$5.80
    Grok 4.3
    xAI · Proprietary
    		38%$3.75
    GPT-5.5 Instant
    OpenAI · Proprietary
    		38%$35.00
    GLM-5.1OSS
    Z AI · Open Source
    		37.3%$5.80
    GPT-5.2
    OpenAI · Proprietary
    		35.4%$15.75
    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 SimpleQA right now?

    As of August 20, 2026, DeepSeek-V3.2-Exp by DeepSeek is #1 for SimpleQA at 97.1%. Ranked by SimpleQA, which checks whether the model makes up facts. This board also tracks SimpleQA. Next on the same board: Grok 4 Fast and DeepSeek-V3.1. This simpleqa leaderboard ranks models by SimpleQA. Scores come from public evals. Prices are the live API rates in the table above.

    Sources: SimpleQA (OpenAI) (https://openai.com/index/introducing-simpleqa/); 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 simpleqa. Ranked by SimpleQA, which checks whether the model makes up facts. Input and output are dollars per million tokens.
    RankModelSimpleQAInput /MOutput /M
    1DeepSeek-V3.2-Exp97.1%$0.27$0.41
    2Grok 4 Fast95%$0.20$0.50
    3DeepSeek-V3.193.4%$0.27$1.00
    4DeepSeek-R1-052892.3%$0.55$2.19
    5Gemini 3.1 Pro77.3%$2.50$15.00
    6Gemini 3 Pro72.1%$2.00$12.00
    7GPT-5.6 Sol71.6%$5.00$30.00
    8Gemini 3.7 Flash71.2%$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

    SimpleQA FAQ

    Who ranks #1 on the SimpleQA leaderboard?

    As of August 20, 2026, DeepSeek-V3.2-Exp by DeepSeek ranks #1 on SimpleQA at 97.1%. API pricing is $0.27/M input and $0.41/M output.

    What are the top models on SimpleQA?

    The current SimpleQA ranking as of August 20, 2026 is 1. DeepSeek-V3.2-Exp at 97.1%; 2. Grok 4 Fast at 95%; 3. DeepSeek-V3.1 at 93.4%.

    Which simpleqa model is the cheapest?

    Gemma 3 4B is the cheapest scored model on this simpleqa leaderboard at $0.02/M input and $0.04/M output ($0.06 blended). DeepSeek-V3.2-Exp still leads SimpleQA at 97.1%.

    Should I always pick the #1 SimpleQA model?

    Not automatically. DeepSeek-V3.2-Exp leads SimpleQA, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh SimpleQA against input/output price, context window, and related evals.

    How often is the SimpleQA 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 SimpleQA?

    SimpleQA — tests factual accuracy on straightforward questions, measuring hallucination rates. This page ranks models that have published a SimpleQA score, with live API token prices on the same row. Official methodology: SimpleQA (OpenAI) (https://openai.com/index/introducing-simpleqa/).

    Where is the SimpleQA leaderboard?

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

    The official SimpleQA (OpenAI) page owns the methodology. This page keeps the published SimpleQA score next to live API $/M so you can pick a production SKU, not only a trophy number. Source: https://openai.com/index/introducing-simpleqa/