llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Capability ranking

Best AI for Knowledge

Use this knowledge model leaderboard to compare the current ranking from the LLMBoard Knowledge Score after applying benchmark evidence requirements.

Updated 2026-08-17

On this page

  • Ranking
  • Overview
  • Leaders
  • Capability
  • Value
  • Composition
  • Compare
  • Top models
  • FAQ

Knowledge Model Leaderboard Ranking

This leaderboard ranking orders models by their LLMBoard Knowledge Score aggregated from eligible benchmark evidence.

30 of 113 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Knowledge Score
Context
Official input / 1M
Official output / 1M
Rank01ModelANClaude MythosAnthropicLLMBoard Knowledge Score99.8ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank02ModelMEMuse SparkMetaLLMBoard Knowledge Score96.9ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank03ModelOPGPT-4.5OpenAILLMBoard Knowledge Score91.1Context128KOfficial input / 1MN/AOfficial output / 1MN/A
Rank04ModelBYSeed 2.1 ProByteDanceLLMBoard Knowledge Score89.8Context256KOfficial input / 1MN/AOfficial output / 1MN/A
Rank05ModelGOGemini 3.1 ProGoogleLLMBoard Knowledge Score89.8Context1MOfficial input / 1M$2Official output / 1M$12
Rank06ModelANClaude Opus 4.7AnthropicLLMBoard Knowledge Score89.5Context1MOfficial input / 1M$5Official output / 1M$25
Rank07ModelACQwen3.7 MaxAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score88.9Context1MOfficial input / 1M$2.5Official output / 1M$7.5
Rank08ModelANClaude Opus 4.6AnthropicLLMBoard Knowledge Score87.1Context1MOfficial input / 1M$5Official output / 1M$25
Rank09ModelMAKimi K2.5Moonshot AILLMBoard Knowledge Score86.7Context262.1KOfficial input / 1M$0.60Official output / 1M$3
Rank10ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score86.5Context1MOfficial input / 1M$0.50Official output / 1M$3
Rank11ModelBYSeed 2.1 TurboByteDanceLLMBoard Knowledge Score85.3Context256KOfficial input / 1MN/AOfficial output / 1MN/A
Rank12ModelACQwen3.5 122B A10BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score84.4Context262.1KOfficial input / 1M$0.40Official output / 1M$3.2
Rank13ModelACQwen3.7 PlusAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score83.1Context1MOfficial input / 1M$0.50Official output / 1M$3
Rank14ModelBAERNIE 5.0BaiduLLMBoard Knowledge Score82.2ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank15ModelOPo1OpenAILLMBoard Knowledge Score82.1Context200KOfficial input / 1M$15Official output / 1M$60
Rank16ModelACQwen3.5 397B A17BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score82.1Context262.1KOfficial input / 1M$0.60Official output / 1M$3.6
Rank17ModelMAKimi K2 ThinkingMoonshot AILLMBoard Knowledge Score80.7Context262.1KOfficial input / 1M$0.60Official output / 1M$2.5
Rank18ModelGOGemini 2.5 ProGoogleLLMBoard Knowledge Score78.5Context1MOfficial input / 1M$1.25Official output / 1M$10
Rank19ModelACQwen3.5 27BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score77.5Context262.1KOfficial input / 1M$0.30Official output / 1M$2.4
Rank20ModelANClaude Sonnet 4.6AnthropicLLMBoard Knowledge Score77.3Context1MOfficial input / 1M$3Official output / 1M$15
Rank21ModelNVNemotron 3 UltraNVIDIALLMBoard Knowledge Score76.7Context1MOfficial input / 1M$0.50Official output / 1M$2.5
Rank22ModelGOGemini 3 ProGoogleLLMBoard Knowledge Score74.5Context1MOfficial input / 1MN/AOfficial output / 1MN/A
Rank23ModelZAGLM 4.7Zhipu AILLMBoard Knowledge Score73.7Context204.8KOfficial input / 1M$0.60Official output / 1M$2.2
Rank24ModelACQwen3.5 35B A3BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score70.7Context262.1KOfficial input / 1M$0.25Official output / 1M$2
Rank25ModelACQwen3.6 27BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score70.5Context262.1KOfficial input / 1M$0.60Official output / 1M$3.6
Rank26ModelMIMAI Thinking 1MicrosoftLLMBoard Knowledge Score70.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank27ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score70.3Context262.1KOfficial input / 1M$0.70Official output / 1M$2.8
Rank28ModelOPGPT-5.2OpenAILLMBoard Knowledge Score69.7Context400KOfficial input / 1M$1.75Official output / 1M$14
Rank29ModelDEDeepSeek-R1DeepSeekLLMBoard Knowledge Score69.4Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank30ModelGOGemini 3 FlashGoogleLLMBoard Knowledge Score69.0Context1MOfficial input / 1M$0.50Official output / 1M$3
Rank31ModelMIMiniMax M2.1MiniMaxLLMBoard Knowledge Score68.1Context204.8KOfficial input / 1M$0.30Official output / 1M$1.2
Rank32ModelXAGrok 4 FastxAILLMBoard Knowledge Score66.8Context2MOfficial input / 1MN/AOfficial output / 1MN/A
Rank33ModelTMInkling SmallThinking Machines LabLLMBoard Knowledge Score66.3Context1MOfficial input / 1MN/AOfficial output / 1MN/A
Rank34ModelACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score66.3ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank35ModelGOGemma 4 31BGoogleLLMBoard Knowledge Score66.2Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank36ModelDEDeepSeek-V3.1DeepSeekLLMBoard Knowledge Score65.7Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank37ModelACQwen3 Next 80B A3B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score64.5Context131.1KOfficial input / 1M$0.50Official output / 1M$6
Rank38ModelACQwen3 VL 235B A22BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score64.4Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank39ModelXIMiMo V2.5 ProXiaomiLLMBoard Knowledge Score62.6Context1MOfficial input / 1M$0.435Official output / 1M$0.87
Rank40ModelMAKimi k1.5Moonshot AILLMBoard Knowledge Score61.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank41ModelXIMiMo V2 FlashXiaomiLLMBoard Knowledge Score61.4Context262.1KOfficial input / 1M$0.14Official output / 1M$0.28
Rank42ModelACQwen3 235B A22B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score61.0Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank43ModelACQwen3.6 35B A3BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score60.8Context262.1KOfficial input / 1M$0.248Official output / 1M$1.49
Rank44ModelGOGemma 2 27BGoogleLLMBoard Knowledge Score59.8ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank45ModelGOGemini 2.0 FlashGoogleLLMBoard Knowledge Score59.5Context1MOfficial input / 1MN/AOfficial output / 1MN/A
Rank46ModelNVNemotron 3 SuperNVIDIALLMBoard Knowledge Score59.3Context262.1KOfficial input / 1M$0.20Official output / 1M$0.80
Rank47ModelGOGemini 2.5 FlashGoogleLLMBoard Knowledge Score58.0Context1MOfficial input / 1M$0.30Official output / 1M$2.5
Rank48ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score55.7Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank49ModelNVLlama 3.1 Nemotron 70BNVIDIALLMBoard Knowledge Score52.4Context128KOfficial input / 1MN/AOfficial output / 1MN/A
Rank50ModelACQwen3 Next 80B A3BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score52.2Context131.1KOfficial input / 1M$0.50Official output / 1M$2
Rank51ModelGOGemma 4 26B A4BGoogleLLMBoard Knowledge Score52.1Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank52ModelACQwen3.5 9BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score51.5Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank53ModelMIPhi 3.5 MoEMicrosoftLLMBoard Knowledge Score50.8ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank54ModelZAGLM 4.5Zhipu AILLMBoard Knowledge Score50.4Context131.1KOfficial input / 1M$0.60Official output / 1M$2.2
Rank55ModelGOGemini 2.0 Flash LiteGoogleLLMBoard Knowledge Score49.8Context1MOfficial input / 1MN/AOfficial output / 1MN/A
Rank56ModelIBGranite 3.3 8BIBMLLMBoard Knowledge Score49.1Context128KOfficial input / 1MN/AOfficial output / 1MN/A
Rank57ModelOPGPT-4.1OpenAILLMBoard Knowledge Score48.8Context1MOfficial input / 1M$2Official output / 1M$8
Rank58ModelMIPhi 4 MiniMicrosoftLLMBoard Knowledge Score48.3Context128KOfficial input / 1M$0.075Official output / 1M$0.30
Rank59ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score46.8Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank60ModelOPo3 miniOpenAILLMBoard Knowledge Score46.8Context200KOfficial input / 1M$1.1Official output / 1M$4.4
Rank61ModelMIMiniMax M2MiniMaxLLMBoard Knowledge Score43.3Context196.6KOfficial input / 1M$0.30Official output / 1M$1.2
Rank62ModelGOGemini 2.5 Flash LiteGoogleLLMBoard Knowledge Score43.3Context1MOfficial input / 1M$0.10Official output / 1M$0.40
Rank63ModelMIPhi 3.5 miniMicrosoftLLMBoard Knowledge Score43.1Context128KOfficial input / 1MN/AOfficial output / 1MN/A
Rank64ModelACQwen3 VL 32BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score42.6ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank65ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score42.6Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank66ModelNVNemotron 3.5 LightningNVIDIALLMBoard Knowledge Score41.9Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank67ModelGOGemini 3.1 Flash LiteGoogleLLMBoard Knowledge Score41.6Context1MOfficial input / 1M$0.25Official output / 1M$1.5
Rank68ModelACQwen3 VL 30B A3BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score40.9Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank69ModelSASarvam 105BSarvam AILLMBoard Knowledge Score40.6Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank70ModelACQwen2.5 14BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score39.9ContextN/AOfficial input / 1M$0.35Official output / 1M$1.4
Rank71ModelGOGemma 2 9BGoogleLLMBoard Knowledge Score39.9ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank72ModelNRHermes 3 70BNous ResearchLLMBoard Knowledge Score39.8Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank73ModelMAMistral Small 3.1 24BMistral AILLMBoard Knowledge Score39.3ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank74ModelNVNemotron 3 NanoNVIDIALLMBoard Knowledge Score39.3Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank75ModelOPGPT-4.1-miniOpenAILLMBoard Knowledge Score38.8Context1MOfficial input / 1M$0.40Official output / 1M$1.6
Rank76ModelZAGLM 4.5 AirZhipu AILLMBoard Knowledge Score38.3Context131.1KOfficial input / 1M$0.20Official output / 1M$1.1
Rank77ModelMAKimi K2Moonshot AILLMBoard Knowledge Score37.9ContextN/AOfficial input / 1M$0.60Official output / 1M$2.5
Rank78ModelGODiffusionGemma 26B A4BGoogleLLMBoard Knowledge Score37.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank79ModelACQwen2.5 32BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score37.1ContextN/AOfficial input / 1M$0.70Official output / 1M$2.8
Rank80ModelGOGemma 3 27BGoogleLLMBoard Knowledge Score36.6Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank81ModelACQwen3.5 4BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score36.4ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank82ModelMAMistral Large 3Mistral AILLMBoard Knowledge Score36.1Context262.1KOfficial input / 1M$0.50Official output / 1M$1.5
Rank83ModelOPGPT-4oOpenAILLMBoard Knowledge Score35.1Context128KOfficial input / 1M$2.5Official output / 1M$10
Rank84ModelGOGemma 3 12BGoogleLLMBoard Knowledge Score34.3Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank85ModelALJamba 1.5 LargeAI21 LabsLLMBoard Knowledge Score34.0Context256KOfficial input / 1MN/AOfficial output / 1MN/A
Rank86ModelACQwen3 VL 4BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score33.5Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank87ModelMIMiniMax M1 80KMiniMaxLLMBoard Knowledge Score31.7Context1MOfficial input / 1MN/AOfficial output / 1MN/A
Rank88ModelCOCommand R+CohereLLMBoard Knowledge Score31.1Context128KOfficial input / 1M$2.5Official output / 1M$10
Rank89ModelGOGemma 4 12BGoogleLLMBoard Knowledge Score29.8ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank90ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score29.8Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank91ModelMIMiniMax M1 40KMiniMaxLLMBoard Knowledge Score29.3ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank92ModelGOGemma 4 E4BGoogleLLMBoard Knowledge Score26.8Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank93ModelGOGemma 3n E4B LiteRTGoogleLLMBoard Knowledge Score25.6ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank94ModelMAMistral Small 3.2 24BMistral AILLMBoard Knowledge Score25.6ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank95ModelIBIBM Granite 4.0 TinyIBMLLMBoard Knowledge Score25.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank96ModelACQwen3 VL 8BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score25.1Context262.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank97ModelACQwen2 72BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score24.9ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank98ModelGOGemma 3n E4BGoogleLLMBoard Knowledge Score22.3Context32KOfficial input / 1MN/AOfficial output / 1MN/A
Rank99ModelMIPhi 4MicrosoftLLMBoard Knowledge Score20.2Context16KOfficial input / 1M$0.125Official output / 1M$0.50
Rank100ModelMAMistral NeMoMistral AILLMBoard Knowledge Score18.1Context128KOfficial input / 1M$0.15Official output / 1M$0.15
Rank101ModelACQwen2.5 Coder 32BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score17.4Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank102ModelGOGemma 4 E2BGoogleLLMBoard Knowledge Score14.3Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank103ModelMAMinistral 8BMistral AILLMBoard Knowledge Score13.3Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank104ModelGOGemma 3 4BGoogleLLMBoard Knowledge Score13.3Context131.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank105ModelACQwen3.5 2BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score13.2ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank106ModelACQwen2 7BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score12.2ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank107ModelALJamba 1.5 MiniAI21 LabsLLMBoard Knowledge Score11.4Context256.1KOfficial input / 1MN/AOfficial output / 1MN/A
Rank108ModelGOGemma 3n E2BGoogleLLMBoard Knowledge Score10.6ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank109ModelGOGemma 3n E2B LiteRTGoogleLLMBoard Knowledge Score10.0ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank110ModelACQwen2.5 Coder 7BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score4.1ContextN/AOfficial input / 1M$0.144Official output / 1M$0.287
Rank111ModelACQwen3.5 0.8BAlibaba Cloud / Qwen TeamLLMBoard Knowledge Score3.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank112ModelGOGemma 3 1BGoogleLLMBoard Knowledge Score0.5ContextN/AOfficial input / 1MN/AOfficial output / 1MN/A
Rank113ModelBAERNIE 4.5BaiduLLMBoard Knowledge Score0.3Context128KOfficial input / 1MN/AOfficial output / 1MN/A

Official PAYG prices appear here. Third-party offers remain on the pricing and model detail pages.

What this leaderboard says

Key findings from the current knowledge leaderboard ranking and its supporting benchmark coverage.

Ranked models113
Vendors22
Open-weight models34
Official prices47
Top knowledge modelClaude Mythos99.8 knowledge scoreBest open-weight modelKimi K2.5Rank #9Lowest official inputPhi 4 Mini$0.07 / 1MLargest contextGrok 4 Fast2M tokens

Claude Mythos leads this page at 99.8, 2.8 points ahead of Muse Spark.

Kimi K2.5 is the highest-ranked open-weight option at #9. Phi 4 Mini has the lowest official input price among ranked models.

Knowledge Leaderboard Leaders

The leading knowledge scores in this benchmark-backed ranking, with the axis focused on the competitive leaderboard range.

Top knowledge models

Knowledge Benchmark Profile

Compare knowledge benchmark strength with each model's broader capability score and leaderboard position.

ModelReasoningKnowledgeMathCodingInstruction
Claude MythosAnthropic99.899.8100.098.8N/A
Muse SparkMeta70.496.9N/A48.6N/A
GPT-4.5OpenAI42.991.148.733.241.0
Seed 2.1 ProByteDance90.189.832.754.5N/A
Gemini 3.1 ProGoogle96.589.8N/A54.2N/A
30.349.368.287.1106.1-7.519.646.773.7100.8LLMBoard Knowledge ScoreLLMBoard Overall Score
80 models with comparable dataOpen a model by selecting its logo
GPQA94.6%Claude Mythos Preview96 compared models
MMLU-Pro89.6%Qwen3.7 Max81 compared models
AIME 2025100.0%Gemini 3 Pro44 compared models
SWE-Bench Verified93.9%Claude Mythos Preview48 compared models
Include86.2%Qwen3.7 Max29 compared models
Aider-Polyglot82.2%Gemini 2.5 Pro Preview 06-0512 compared models
MAXIFE89.2%Qwen3.7 Max11 compared models
NOVA-6359.1%Qwen3.5-397B-A17B11 compared models

Capability at each price point

Official vendor API prices plotted against the knowledge metric used on this page. Price remains a separate decision signal.

020406080100$0.1$0.2$0.5$1.0$2.0$5.0$10$20LLMBoard Knowledge ScoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier47 models with official PAYG prices

Knowledge Leaderboard Composition

Vendor concentration and model access among the first 25 products in the ranking.

Top-model vendor mix

25 models
Alibaba Cloud / Qwen Team8Anthropic4Google3OpenAI2ByteDance2Moonshot AI2Meta1Baidu1

Access model

Open weights
8
Closed weights
17
Official price available
18

Compare the leaders

Open focused comparisons between the current leader and the nearest practical alternatives.

Claude MythosvsMuse SparkClaude MythosvsKimi K2.5Claude MythosvsPhi 4 Mini
Overall leaderboardCoding leaderboardReasoning leaderboardMath leaderboardInstruction leaderboard

The Top AI Models for Knowledge

A data-backed look at the first five models in this knowledge leaderboard ranking, including benchmark context, price and output speed where available.

Ranking basisThis knowledge AI model leaderboard uses the knowledge capability score shown on this page. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    AN
    Claude MythosAnthropic
    LLMBoard Knowledge Score
    99.8

    Strengths

    • Ranks #1 with 99.8 LLMBoard Knowledge Score

    Considerations

    • Weights are not marked as open
  2. 02
    ME
    Muse SparkMeta
    LLMBoard Knowledge Score
    96.9

    Strengths

    • Ranks #2 with 96.9 LLMBoard Knowledge Score

    Considerations

    • Evidence coverage is 60%
    • Weights are not marked as open
  3. 03
    OP
    GPT-4.5OpenAI
    LLMBoard Knowledge Score
    91.1
    Speed
    Up to 50 tok/s via OpenAI

    Strengths

    • Ranks #3 with 91.1 LLMBoard Knowledge Score
    • 128K-token context window

    Considerations

    • Weights are not marked as open
  4. 04
    BY
    Seed 2.1 ProByteDance
    LLMBoard Knowledge Score
    89.8

    Strengths

    • Ranks #4 with 89.8 LLMBoard Knowledge Score
    • 256K-token context window

    Considerations

    • Weights are not marked as open
  5. 05
    GO
    Gemini 3.1 ProGoogle
    LLMBoard Knowledge Score
    89.8
    Price
    $2.0 input / $12 output per 1M tokens
    Speed
    Up to 23 tok/s via Google

    Strengths

    • Ranks #5 with 89.8 LLMBoard Knowledge Score
    • Lowest official input price among the current top five
    • 1M-token context window

    Considerations

    • Evidence coverage is 60%
    • Weights are not marked as open

Selection summary

Best AI Models for Knowledge

Claude Mythos is currently the best-ranked LLM for knowledge with a 99.8 knowledge score. The score is a relative ranking signal, so price, speed, context and evidence coverage should still be checked separately.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Capability rank #1Claude Mythos99.8Capability rank #2Muse Spark96.9Capability rank #3GPT-4.5Up to 50 tok/s via OpenAI

About this leaderboard

Common questions about the Best AI for Knowledge leaderboard, benchmark evidence and ranking method.

What is the best model on Best AI for Knowledge?

Claude Mythos is currently ranked first with a knowledge score of 99.8.

How is this leaderboard ranked?

Each model appears once using its current scored version. The leaderboard ranking follows the capability named in the title, while the overall page uses the LLMBoard score aggregated from eligible benchmark evidence.

How many models are included?

This page currently ranks 113 unique model products.

Where does pricing come from?

Main price columns use the model vendor's official standard PAYG API rate. Eligible third-party offers appear only in separately labeled columns, and unavailable official prices display as N/A.

Does Arena affect the score?

No. Arena results are displayed as an independent signal and are not included in the current LLMBoard capability score.