AnotherWrapper
    $249
    LLMImageVideoSpeechTranscription

    MGSM

    🏆 Leaderboard

    As of August 20, 2026, Claude Opus 4.5 is #1 for MGSM at 94.8%. Ranked by the MGSM score 61 models in this index have a published MGSM score. MGSM leaderboard: rank models by MGSM next to live API token prices.

    Updated August 20, 2026282 models33 providers
    Claude Opus 4.5
    Anthropic · Proprietary
    		94.8%$30.00
    Claude Opus 4.1
    Anthropic · Proprietary
    		94.2%$90.00
    GPT-5.2
    OpenAI · Proprietary
    		94%$15.75
    Gemini 3 Pro
    Google · Proprietary
    		93.9%$14.00
    Claude Opus 4
    Anthropic · Proprietary
    		93.8%$90.00
    o4-mini
    OpenAI · Proprietary
    		93.4%$5.50
    Gemini 3 Flash
    Google · Proprietary
    		93.3%$3.50
    Claude Sonnet 4
    Anthropic · Proprietary
    		93.0%$18.00
    GPT-5.1
    OpenAI · Proprietary
    		93.0%$11.25
    GPT-5
    OpenAI · Proprietary
    		92.8%$11.25
    GPT-5 mini
    OpenAI · Proprietary
    		92.6%$2.25
    Claude 3.7 Sonnet
    Anthropic · Proprietary
    		92.4%$18.00
    Llama 4 MaverickOSS
    Meta · Open Source
    		92.3%$1.02
    DeepSeek-R1OSS
    DeepSeek · Open Source
    		92.3%$2.74
    DeepSeek-V3OSS
    DeepSeek · Open Source
    		92.2%$1.37
    GPT OSS 120BOSS
    OpenAI · Open Source
    		92.0%$0.54
    o3-mini
    OpenAI · Proprietary
    		92%$5.50
    Qwen3 Max
    Qwen · Proprietary
    		91.8%$5.50
    o3
    OpenAI · Proprietary
    		91.8%$10.00
    DeepSeek-V3 0324OSS
    DeepSeek · Open Source
    		91.7%$1.42
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		91.6%$18.00
    Claude 3.5 Sonnet
    Anthropic · Proprietary
    		91.6%$18.00
    Grok-3
    xAI · Proprietary
    		91.3%$18.00
    Llama 3.3 70B InstructOSS
    Meta · Open Source
    		91.1%$0.40
    Kimi K2 InstructOSS
    Moonshot AI · Open Source
    		91.0%$1.00
    Grok-4 Fast Reasoning
    xAI · Proprietary
    		90.9%$0.70
    GLM-4.5OSS
    Z AI · Open Source
    		90.8%$2.80
    o1-preview
    OpenAI · Proprietary
    		90.8%$75.00
    Claude 3 Opus
    Anthropic · Proprietary
    		90.7%$90.00
    GPT-4o
    OpenAI · Proprietary
    		90.7%$12.50
    Llama 4 ScoutOSS
    Meta · Open Source
    		90.6%$0.38
    GPT-4o
    OpenAI · Proprietary
    		90.5%$12.50
    GLM-4.6OSS
    Z AI · Open Source
    		89.8%$2.80
    Grok-4.1 Fast Reasoning
    xAI · Proprietary
    		89.5%$0.70
    GPT-5 nano
    OpenAI · Proprietary
    		89.3%$0.45
    o1
    OpenAI · Proprietary
    		89.3%$75.00
    GPT OSS 20BOSS
    OpenAI · Open Source
    		89.0%$0.25
    GPT-4 Turbo
    OpenAI · Proprietary
    		88.5%$40.00
    GLM-4.7OSS
    Z AI · Open Source
    		88.2%$2.80
    Grok-4 Fast Non-Reasoning
    xAI · Proprietary
    		88%$0.70
    MiniMax M2.1OSS
    MiniMax · Open Source
    		87.8%$1.50
    GPT-4.1 mini
    OpenAI · Proprietary
    		87.8%$2.00
    GPT-4.1
    OpenAI · Proprietary
    		87.7%$10.00
    Grok-4.1 Fast Non-Reasoning
    xAI · Proprietary
    		87.6%$0.70
    Gemini 1.5 Pro
    Google · Proprietary
    		87.5%$12.50
    GPT-4o mini
    OpenAI · Proprietary
    		87%$0.75
    Llama 3.2 90B InstructOSS
    Meta · Open Source
    		86.9%$0.75
    Claude 3.5 Haiku
    Anthropic · Proprietary
    		85.6%$4.80
    Qwen3 235B A22BOSS
    Qwen · Open Source
    		83.5%$0.20
    Claude 3 Sonnet
    Anthropic · Proprietary
    		83.5%$18.00
    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.

    Get the stack — $249Have 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 MGSM right now?

    As of August 20, 2026, Claude Opus 4.5 by Anthropic is #1 for MGSM at 94.8%. Ranked by the MGSM score This board also tracks MGSM. Next on the same board: Claude Opus 4.1 and GPT-5.2. This mgsm leaderboard ranks models by MGSM. 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 mgsm. Ranked by the MGSM score Input and output are dollars per million tokens.
    RankModelMGSMInput /MOutput /M
    1Claude Opus 4.594.8%$5.00$25.00
    2Claude Opus 4.194.2%$15.00$75.00
    3GPT-5.294%$1.75$14.00
    4Gemini 3 Pro93.9%$2.00$12.00
    5Claude Opus 493.8%$15.00$75.00
    6o4-mini93.4%$1.10$4.40
    7Gemini 3 Flash93.3%$0.50$3.00
    8Claude Sonnet 493.0%$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

    MGSM FAQ

    Who ranks #1 on the MGSM leaderboard?

    As of August 20, 2026, Claude Opus 4.5 by Anthropic ranks #1 on MGSM at 94.8%. API pricing is $5.00/M input and $25.00/M output.

    What are the top models on MGSM?

    The current MGSM ranking as of August 20, 2026 is 1. Claude Opus 4.5 at 94.8%; 2. Claude Opus 4.1 at 94.2%; 3. GPT-5.2 at 94%.

    Which mgsm model is the cheapest?

    Llama 3.2 3B Instruct is the cheapest scored model on this mgsm leaderboard at $0.01/M input and $0.02/M output ($0.03 blended). Claude Opus 4.5 still leads MGSM at 94.8%.

    Should I always pick the #1 MGSM model?

    Not automatically. Claude Opus 4.5 leads MGSM, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh MGSM against input/output price, context window, and related evals.

    How often is the MGSM 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 MGSM?

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

    Where is the MGSM leaderboard?

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

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