AnotherWrapper
    Build with the APIs
    LLMImageVideoSpeechTranscription

    SWE-bench Multilingual

    🏆 Leaderboard

    As of August 31, 2026, Claude Mythos Preview is #1 for SWE-bench Multilingual at 87.3%. Ranked by the SWE-bench Multilingual score 42 models in this index have a published SWE-bench Multilingual score. SWE-bench Multilingual leaderboard with live API prices. SWE-bench Multilingual — a multilingual software engineering benchmark derived from SWE-bench tasks across multiple languages and locales.

    Updated August 31, 2026345 models36 providers

    SWE-bench Multilingual vs price

    42 models. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price — a dot under it is a worse deal than something on the line.

    Best score at each price#1 on this board
    Claude Mythos Preview
    Anthropic · Proprietary
    		87.3%$60.00
    Claude Opus 4.8
    Anthropic · Proprietary
    		84.4%$30.00
    Qwen3.8-Flash-NextOSS
    Qwen · Open Source
    		81%$0.62
    Qwen3.8 Flash
    Qwen · Proprietary
    		81%$0.62
    Laguna S 2.1OSS
    Poolside · Open Source
    		78.5%$0.30
    Qwen3.7 Max
    Qwen · Proprietary
    		78.3%$5.00
    Claude Sonnet 5
    Anthropic · Proprietary
    		78.3%$12.00
    Claude Opus 4.6
    Anthropic · Proprietary
    		77.8%$30.00
    Claude Mythos 5
    Anthropic · Proprietary
    		77.8%$60.00
    Kimi K2.6OSS
    Moonshot AI · Open Source
    		76.7%$4.93
    MiniMax M2.7OSS
    MiniMax · Open Source
    		76.5%$1.50
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek · Open Source
    		76.2%$5.22
    Qwen3.7-Plus
    Qwen · Proprietary
    		75.8%$1.60
    Hy3OSS
    Tencent · Open Source
    		75.8%$0.66
    Qwen3.6 Plus
    Qwen · Proprietary
    		73.8%$3.50
    Composer 2 Fast
    Cursor · Proprietary
    		73.7%$9.00
    Composer 2
    Cursor · Proprietary
    		73.7%$3.00
    DeepSeek-V4-Flash-MaxOSS
    DeepSeek · Open Source
    		73.3%$0.42
    Kimi K2.5OSS
    Moonshot AI · Open Source
    		73%$3.68
    MiniMax M2.1OSS
    MiniMax · Open Source
    		72.5%$1.50
    MiMo-V2-Pro
    Xiaomi · Proprietary · via OpenRouter
    		71.7%$1.30
    MiMo-V2-FlashOSS
    Xiaomi · Open Source
    		71.7%$0.40
    Qwen3.6-27BOSS
    Qwen · Open Source
    		71.3%$4.20
    DeepSeek-V4-Flash-0423OSS
    DeepSeek · Open Source
    		70.2%$0.30
    DeepSeek-V3.2OSS
    DeepSeek · Open Source · via OpenRouter
    		70.2%$0.57
    Qwen3.5-397B-A17BOSS
    Qwen · Open Source
    		69.3%$4.20
    Nemotron 3 Ultra (550B A55B)OSS
    NVIDIA · Open Source · via OpenRouter
    		67.7%$2.70
    Qwen3.6-35B-A3BOSS
    Qwen · Open Source · via OpenRouter
    		67.2%$1.14
    GLM-4.7OSS
    Z AI · Open Source
    		66.7%$2.80
    MAI-Code-1-Flash
    Microsoft · Proprietary
    		65.5%$0.75
    Laguna XS 2.1OSS
    Poolside · Open Source
    		63.1%$0.30
    Kimi K2-Thinking-0905OSS
    Moonshot AI · Open Source
    		61.1%$2.47
    DeepSeek-V3.2-ExpOSS
    DeepSeek · Open Source
    		57.9%$0.68
    MiniMax M2OSS
    MiniMax · Open Source
    		56.5%$1.50
    Qwen3-Coder 480B A35B InstructOSS
    Qwen · Open Source · via OpenRouter
    		54.7%$2.02
    DeepSeek-V3.1OSS
    DeepSeek · Open Source
    		54.5%$1.27
    Kimi K2-Instruct-0905OSS
    Moonshot AI · Open Source · via OpenRouter
    		47.3%$3.10
    Kimi K2 InstructOSS
    Moonshot AI · Open Source
    		47.3%$1.00
    Nemotron 3 Super (120B A12B)OSS
    NVIDIA · Open Source · via OpenRouter
    		45.8%$0.54
    Nemotron 3.5 Lightning (30B A3B)OSS
    NVIDIA · Open Source
    		39.3%$0.25
    LongCat-Flash-LiteOSS
    Meituan · Open Source
    		38.1%$0.50
    DeepSeek-R1-0528OSS
    DeepSeek · Open Source
    		30.5%$2.74
    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
    Showing 1–50 of 345 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

    345 models across 36 providers. Search or jump to a lab — every model page stays linked here.

    OpenAI52Anthropic22Google34Cursor2xAI17DeepSeek20MiniMax7Qwen55AI21 Labs2Amazon7Baidu2ByteDance4Cohere4IBM2Inception1inclusionAI1LG AI Research1Liquid AI2Meituan4Meta12Microsoft9Mistral26Moonshot AI11Nous Research1NVIDIA9OpenBMB1Poolside2Sakana AI1Sarvam AI2StepFun2Tencent1Thinking Machines1Unisound1Upstage1Xiaomi5Z AI21

    Baidu

    2 models
    ERNIE 5.0ERNIE 4.5

    Inception

    1 models
    Mercury 2

    inclusionAI

    1 models
    Ling-3.0-flash

    LG AI Research

    1 models
    K-EXAONE-236B-A23B

    Liquid AI

    2 models
    LFM2.5-VL-3BLFM2.5-2.6B

    Nous Research

    1 models
    Hermes 3 70B

    OpenBMB

    1 models
    MiniCPM-SALA

    Sakana AI

    1 models
    Sakana Namazu

    Sarvam AI

    2 models
    Sarvam-105BSarvam-30B

    Tencent

    1 models
    Hy3

    Thinking Machines

    1 models
    Inkling-Small

    Unisound

    1 models
    U2

    Upstage

    1 models
    Solar Pro 4

    Which model leads SWE-bench Multilingual right now?

    As of August 31, 2026, Claude Mythos Preview by Anthropic is #1 for SWE-bench Multilingual at 87.3%. Ranked by the SWE-bench Multilingual score This board also tracks SWE-bench Multilingual. Next on the same board: Claude Opus 4.8 and Qwen3.8 Flash. This swe-bench multilingual leaderboard ranks models by SWE-bench Multilingual. 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 swe-bench multilingual. Ranked by the SWE-bench Multilingual score Input and output are dollars per million tokens.
    RankModelSWE-bench MultilingualInput /MOutput /M
    1Claude Mythos Preview87.3%$10.00$50.00
    2Claude Opus 4.884.4%$5.00$25.00
    3Qwen3.8 Flash81%$0.15$0.47
    4Qwen3.8-Flash-Next81%$0.15$0.47
    5Laguna S 2.178.5%$0.10$0.20
    6Claude Sonnet 578.3%$2.00$10.00
    7Qwen3.7 Max78.3%$1.25$3.75
    8Claude Opus 4.677.8%$5.00$25.00

    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

    SWE-bench Multilingual FAQ

    Who ranks #1 on the SWE-bench Multilingual leaderboard?

    As of August 31, 2026, Claude Mythos Preview by Anthropic ranks #1 on SWE-bench Multilingual at 87.3%. API pricing is $10.00/M input and $50.00/M output.

    What are the top models on SWE-bench Multilingual?

    The current SWE-bench Multilingual ranking as of August 31, 2026 is 1. Claude Mythos Preview at 87.3%; 2. Claude Opus 4.8 at 84.4%; 3. Qwen3.8 Flash at 81%.

    Which swe-bench multilingual model is the cheapest?

    Nemotron 3.5 Lightning (30B A3B) is the cheapest scored model on this swe-bench multilingual leaderboard at $0.05/M input and $0.20/M output ($0.25 blended). Claude Mythos Preview still leads SWE-bench Multilingual at 87.3%.

    Should I always pick the #1 SWE-bench Multilingual model?

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

    How often is the SWE-bench Multilingual leaderboard updated?

    Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 31, 2026. Treat it as a current index, not a one-off blog post.

    What is SWE-bench Multilingual?

    SWE-bench Multilingual — a multilingual software engineering benchmark derived from SWE-bench tasks across multiple languages and locales. This page ranks models that have published a SWE-bench Multilingual score, with live API token prices on the same row.

    Where is the SWE-bench Multilingual leaderboard?

    This page is the SWE-bench Multilingual leaderboard. Models are sorted by SWE-bench Multilingual, 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 SWE-bench Multilingual ranking different from the official board?

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