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 Directory

Scoring & Data

Scoring & Data
1367 models808 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Open weights

Open Model Leaderboard

Use this open model leaderboard to compare the current open-weight ranking from aggregated benchmark evidence, capability, context, licenses, pricing and runtime.

Data as of 2026-10-22

On this page

  • Ranking
  • Overview
  • Capability
  • Landscape
  • Value
  • Top models
  • FAQ

Open Model Leaderboard Ranking

This leaderboard ranks each model using its latest scored open-weight version and eligible benchmark evidence.

30 of 181 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Score
License
Parameters
Context
Official input / 1M
Output speed
Rank01ModelMAKimi K3Moonshot AILLMBoard Score86.25LicenseOpenParameters2.8TContext1MOfficial input / 1M$3Output speedN/A
Rank02ModelACQwen3.8 MaxAlibaba Cloud / Qwen TeamLLMBoard Score85.12LicenseOpenParameters2.4TContext1MOfficial input / 1M$2Output speedN/A
Rank03ModelZAGLM 5.3Zhipu AILLMBoard Score84.35LicenseOpenParameters753BContext1MOfficial input / 1M$1.2Output speedN/A
Rank04ModelSAAtria DawnShanghai AI LaboratoryLLMBoard Score83.28LicenseOpenParameters744BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank05ModelDEDeepSeek-V4.1DeepSeekLLMBoard Score83.21LicenseOpenParameters763.2BContext1MOfficial input / 1M$0.15Output speedN/A
Rank06ModelDEDeepSeek-V4-ProDeepSeekLLMBoard Score83.16LicenseOpenParameters1.6TContext1MOfficial input / 1M$0.66Output speedN/A
Rank07ModelXIMiMo V2.6 ProXiaomiLLMBoard Score81.95LicenseOpenParameters1TContext1MOfficial input / 1M$0.435Output speed13.54 tok/s
Rank08ModelZAGLM 5.3 FlashZhipu AILLMBoard Score81.34LicenseOpenParameters320BContext1MOfficial input / 1M$0.1195Output speed44.69 tok/s
Rank09ModelTEHy4TencentLLMBoard Score81.17LicenseOpenParameters770BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank10ModelACQwen3.8 Flash NextAlibaba Cloud / Qwen TeamLLMBoard Score80.17LicenseOpenParameters125BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank11ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamLLMBoard Score80.07LicenseOpenParameters125BContext1MOfficial input / 1M$0.15Output speedN/A
Rank12ModelZAGLM 5.2Zhipu AILLMBoard Score75.84LicenseOpenParameters753BContext1MOfficial input / 1M$1.2Output speedN/A
Rank13ModelMEMuse Spark OpenMetaLLMBoard Score74.86LicenseOpenParameters816BContext1MOfficial input / 1MN/AOutput speedN/A
Rank14ModelXIMiMo V2.6 FlashXiaomiLLMBoard Score74.68LicenseOpenParameters309BContext1MOfficial input / 1M$0.14Output speedN/A
Rank15ModelACQwen3.8 27BAlibaba Cloud / Qwen TeamLLMBoard Score73.94LicenseOpenParameters27.8BContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank16ModelRABeam 1.0Reflection AILLMBoard Score73.25LicenseOpenParameters501.3BContext1MOfficial input / 1MN/AOutput speedN/A
Rank17ModelMAKimi K2.6Moonshot AILLMBoard Score73.14LicenseOpenParameters1TContext262.1KOfficial input / 1M$0.95Output speedN/A
Rank18ModelINLing 3.0 Flash FinInclusionaiLLMBoard Score71.95LicenseOpenParameters124BContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank19ModelTEHy3TencentLLMBoard Score70.68LicenseOpenParameters295BContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank20ModelMIMiniMax M3MiniMaxLLMBoard Score68.32LicenseOpenParameters428BContext1MOfficial input / 1M$0.30Output speed45.04 tok/s
Rank21ModelZAGLM 5.1Zhipu AILLMBoard Score66.79LicenseOpenParameters754BContext202.8KOfficial input / 1M$0.8964Output speedN/A
Rank22ModelPOLaguna S 2.1PoolsideLLMBoard Score66.14LicenseOpenParameters118BContext1MOfficial input / 1MN/AOutput speedN/A
Rank23ModelMAKimi K2.5Moonshot AILLMBoard Score64.61LicenseOpenParameters1TContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank24ModelMAKimi K2.7 CodeMoonshot AILLMBoard Score64.15LicenseOpenParameters1TContext262.1KOfficial input / 1M$0.95Output speedN/A
Rank25ModelACQwen3.5 397B A17BAlibaba Cloud / Qwen TeamLLMBoard Score63.82LicenseOpenParameters397BContext262.1KOfficial input / 1M$0.60Output speedN/A
Rank26ModelTMInklingThinking Machines LabLLMBoard Score63.48LicenseOpenParameters975BContext524.3KOfficial input / 1MN/AOutput speedN/A
Rank27ModelTMInkling SmallThinking Machines LabLLMBoard Score62.91LicenseOpenParameters276BContext524.3KOfficial input / 1MN/AOutput speedN/A
Rank28ModelNVNemotron 3 UltraNVIDIALLMBoard Score60.75LicenseOpenParameters550BContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank29ModelXIMiMoXiaomiLLMBoard Score60.09LicenseOpenParameters310.8BContext1MOfficial input / 1M$0.14Output speed5.81 tok/s
Rank30ModelINLing 3.0 FlashInclusionaiLLMBoard Score59.67LicenseOpenParameters124BContext131.1KOfficial input / 1MN/AOutput speedN/A

Open-weight status belongs to the scored model version. License terms still need to be checked on the model detail page.

Open Model Leaderboard Overview

Key leaders and coverage signals from the current open-weight ranking.

Ranked open models181Unique model products

Open Model Benchmark Leaders

Each capability benchmark remains a separate score alongside the overall leaderboard.

Reasoning95.20
Knowledge91.26
Math92.85
Coding75.82
Instruction91.51

Open-model leaderboard landscape

Vendor, license and model-size patterns across models in the current ranking.

Top-30 vendor mix

30 models
Alibaba Cloud / Qwen Team5
Moonshot AI4
Zhipu AI4
Xiaomi3
DeepSeek2
Tencent2
Inclusionai2
Thinking Machines Lab2

Scored-version licenses

Apache 2.0
80
MIT
39
Gemma
8
OpenMDW License v1.1
7
Llama 3.1 Community License
7
Proprietary
4
Modified MIT License
3
0.0025.0050.0075.00100.00416.5M4.4B47.3B504.5B5.4TLLMBoard ScoreParameters
181 models with comparable dataOpen a model by selecting its logo

Official price and capability

Only positive official vendor PAYG prices are included. Price and benchmark-backed capability remain separate leaderboard signals.

020406080100$0.1$0.2$0.5$1.0$2.0$5.0LLMBoard scoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier58 models with official PAYG prices

The Top AI Models for Open-Weight Use

The current top five entries in the open model leaderboard, summarized with benchmark capability, official price, output speed and deployment-relevant evidence.

About open-weight models

Common questions about this open model leaderboard, benchmark coverage and ranking.

What is the highest-ranked open-weight model?

Kimi K3 currently leads the open-model leaderboard ranking.

What are the top three open-weight models?

The current leaders are Kimi K3 (86.25 LLMBoard score), Qwen3.8 Max (85.12 LLMBoard score), and GLM 5.3 (84.35 LLMBoard score).

Which open-weight model has the lowest official input price?

Phi 4 Mini Reasoning has the lowest listed official input price at $0.08 per 1M tokens.

Which open-weight models are fastest?

The fastest matched records are Llama 3.3 70B (2,220.00 tok/s via Cerebras), Llama 3.1 8B (2,047.00 tok/s via Cerebras), and Min istral 3 (1,222.00 tok/s via Mistral AI).

Which open-weight model has the largest context window?

Llama 4 Scout has the largest listed context window at 10M tokens.

What does open weights mean here?

The scored model version is marked as having publicly available weights. That flag does not by itself determine whether the license permits every commercial or derivative use.

How many models are ranked?

This page currently ranks 181 unique open-weight models.

Which version is evaluated?

Each row names the latest open-weight version with a current LLMBoard score derived from eligible benchmark evidence.

Top open-weight modelKimi K386.25 LLMBoard score
Largest contextLlama 4 Scout10M tokens
Most recent releaseDeepSeek-V4.12026-10-17
Kimi K3Rank #1 overall
Kimi K3Rank #1 overall
MiMo V2.5 ProRank #53 overall
DeepSeek-V4-ProRank #6 overall
MiMo V2.5 ProRank #53 overall

Ranking basisThis open-weight use AI model leaderboard uses the current LLMBoard capability score among versions marked as open weight. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    MA
    Kimi K3Moonshot AI
    LLMBoard Score
    86.25
    Price
    $3 input / $15 output per 1M tokens

    Strengths

    • Ranks #1 with a 86.25 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens
  2. 02
    AC
    Qwen3.8 MaxAlibaba Cloud / Qwen Team
    LLMBoard Score
    85.12
    Price
    $2 input / $6 output per 1M tokens

    Strengths

    • Ranks #2 with a 85.12 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens
  3. 03
    ZA
    GLM 5.3Zhipu AI
    LLMBoard Score
    84.35
    Price
    $1.2 input / $4.2 output per 1M tokens

    Strengths

    • Ranks #3 with a 84.35 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens
  4. 04
    SA
    Shanghai AI Laboratory
    LLMBoard Score
    83.28

    Strengths

    • Ranks #4 with a 83.28 LLMBoard Score
    • Open-weight model version

    Considerations

    • 0% benchmark coverage
  5. 05
    DE
    DeepSeek
    LLMBoard Score
    83.21
    Price
    $0.15 input / $0.6 output per 1M tokens

    Strengths

    • Ranks #5 with a 83.21 LLMBoard Score
    • Open-weight model version
    • Lowest official input price among the top models

    Considerations

    • 40% benchmark coverage

Selection summary

Best AI Models for Open-Weight Use

Kimi K3 is the highest-ranked open-weight model at 86.25. The best open LLM also depends on license terms, hardware needs, context, price and available runtime records.

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.

Atria Dawn
DeepSeek-V4.1
Open-model rank #1Kimi K3$3 input / $15 output per 1M tokens
Open-model rank #2Qwen3.8 Max$2 input / $6 output per 1M tokens
Open-model rank #3GLM 5.3$1.2 input / $4.2 output per 1M tokens