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
1224 models729 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 2026-09-08

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 166 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Score
License
Parameters
Context
Official input / 1M
Output speed
Rank01ModelMAKimi K3Moonshot AILLMBoard Score89.45LicenseOpenParameters2.8TContext1MOfficial input / 1M$3Output speedN/A
Rank02ModelZAGLM 5.3Zhipu AILLMBoard Score88.97LicenseOpenParameters753BContext1MOfficial input / 1M$1.4Output speed472.69 tok/s
Rank03ModelACQwen3.8 MaxAlibaba Cloud / Qwen TeamLLMBoard Score86.93LicenseOpenParameters2.4TContext1MOfficial input / 1M$2Output speed60.87 tok/s
Rank04ModelDEDeepSeek-V4-ProDeepSeekLLMBoard Score86.78LicenseOpenParameters1.6TContext1MOfficial input / 1MN/AOutput speed45.48 tok/s
Rank05ModelZAGLM 5.3 FlashZhipu AILLMBoard Score84.28LicenseOpenParameters320BContext1MOfficial input / 1M$0.075Output speed74.28 tok/s
Rank06ModelTEHy4TencentLLMBoard Score83.71LicenseOpenParameters770BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank07ModelACQwen3.8 Flash NextAlibaba Cloud / Qwen TeamLLMBoard Score81.44LicenseOpenParameters125BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank08ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamLLMBoard Score81.35LicenseOpenParameters125BContext1MOfficial input / 1M$0.15Output speedN/A
Rank09ModelZAGLM 5.2Zhipu AILLMBoard Score77.02LicenseOpenParameters753BContext1MOfficial input / 1M$1.4Output speed3.96 tok/s
Rank10ModelACQwen3.8 27BAlibaba Cloud / Qwen TeamLLMBoard Score74.94LicenseOpenParameters27.8BContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank11ModelMAKimi K2.6Moonshot AILLMBoard Score73.54LicenseOpenParameters1TContext262.1KOfficial input / 1M$0.95Output speed1.24 tok/s
Rank12ModelTEHy3TencentLLMBoard Score71.35LicenseOpenParameters295BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank13ModelMIMiniMax M3MiniMaxLLMBoard Score69.20LicenseOpenParameters428BContext1MOfficial input / 1M$0.30Output speed6.61 tok/s
Rank14ModelPOLaguna S 2.1PoolsideLLMBoard Score67.97LicenseOpenParameters118BContext1MOfficial input / 1MN/AOutput speedN/A
Rank15ModelZAGLM 5.1Zhipu AILLMBoard Score67.64LicenseOpenParameters754BContext200KOfficial input / 1M$1.4Output speedN/A
Rank16ModelMAKimi K2.5Moonshot AILLMBoard Score65.57LicenseOpenParameters1TContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank17ModelMAKimi K2.7 CodeMoonshot AILLMBoard Score65.53LicenseOpenParameters1TContext262.1KOfficial input / 1M$0.95Output speedN/A
Rank18ModelACQwen3.5 397B A17BAlibaba Cloud / Qwen TeamLLMBoard Score64.55LicenseOpenParameters397BContext262.1KOfficial input / 1M$0.60Output speedN/A
Rank19ModelTMInkling SmallThinking Machines LabLLMBoard Score63.90LicenseOpenParameters276BContext256KOfficial input / 1MN/AOutput speedN/A
Rank20ModelNVNemotron 3 UltraNVIDIALLMBoard Score61.30LicenseOpenParameters550BContextN/AOfficial input / 1M$0.50Output speedN/A
Rank21ModelXIMiMoXiaomiLLMBoard Score60.00LicenseOpenParameters310.8BContext1MOfficial input / 1M$0.14Output speed5.39 tok/s
Rank22ModelMAKimi K2 ThinkingMoonshot AILLMBoard Score59.99LicenseOpenParameters1TContext262.1KOfficial input / 1MN/AOutput speedN/A
Rank23ModelMELongCat Flash ThinkingMeituanLLMBoard Score59.49LicenseOpenParameters560BContext128KOfficial input / 1MN/AOutput speedN/A
Rank24ModelSTStep 3.5 FlashStepFunLLMBoard Score59.42LicenseOpenParameters196BContext65.5KOfficial input / 1M$0.10Output speed21.16 tok/s
Rank25ModelACQwen3.6 27BAlibaba Cloud / Qwen TeamLLMBoard Score58.93LicenseOpenParameters27.8BContext262.1KOfficial input / 1M$0.60Output speedN/A
Rank26ModelZAGLM 4.7Zhipu AILLMBoard Score58.55LicenseOpenParameters358BContext204.8KOfficial input / 1M$0.60Output speedN/A
Rank27ModelGOGemma 4 31BGoogleLLMBoard Score58.54LicenseOpenParameters30.7BContext262.1KOfficial input / 1MN/AOutput speed22.86 tok/s
Rank28ModelACQwen3.5 122B A10BAlibaba Cloud / Qwen TeamLLMBoard Score58.22LicenseOpenParameters122BContext262.1KOfficial input / 1M$0.40Output speedN/A
Rank29ModelMEMuse Glimmer 30BMetaLLMBoard Score57.39LicenseOpenParameters29.6BContextN/AOfficial input / 1MN/AOutput speedN/A
Rank30ModelACQwen3.5 27BAlibaba Cloud / Qwen TeamLLMBoard Score56.05LicenseOpenParameters27BContext262.1KOfficial input / 1M$0.30Output 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 models166Unique model products

Open Model Benchmark Leaders

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

Reasoning97.56
Knowledge86.17
Math92.85
Coding88.17
Instruction86.01

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 Team8
Moonshot AI5
Zhipu AI5
Tencent2
DeepSeek1
MiniMax1
Poolside1
Thinking Machines Lab1

Scored-version licenses

Apache 2.0
75
MIT
35
Gemma
8
Llama 3.1 Community License
7
Proprietary
4
OpenMDW License v1.1
4
Modified MIT License
3
0.0025.0050.0075.00100.00416.5M4.4B47.3B504.5B5.4TLLMBoard ScoreParameters
166 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$0.05$0.1$0.2$0.5$1.0$2.0$5.0LLMBoard scoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier54 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 (89.45 LLMBoard score), GLM 5.3 (88.97 LLMBoard score), and Qwen3.8 Max (86.93 LLMBoard score).

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

Min istral 3 has the lowest listed official input price at $0.04 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 166 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 K389.45 LLMBoard score
Largest contextLlama 4 Scout10M tokens
Most recent releaseHy42026-08-28
Qwen3.8 MaxRank #3 overall
Kimi K2.5Rank #16 overall
MiMo V2.5 ProRank #41 overall
Kimi K3Rank #1 overall
Nemotron 3 UltraRank #20 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
    89.45
    Price
    $3 input / $15 output per 1M tokens

    Strengths

    • Ranks #1 with a 89.45 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens

    Considerations

    • 20% benchmark coverage
  2. 02
    ZA
    GLM 5.3Zhipu AI
    LLMBoard Score
    88.97
    Price
    $1.4 input / $4.4 output per 1M tokens
    Speed
    472.69 tok/s via FriendliAI

    Strengths

    • Ranks #2 with a 88.97 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens

    Considerations

    • 20% benchmark coverage
  3. 03
    AC
    Alibaba Cloud / Qwen Team
    LLMBoard Score
    86.93
    Price
    $2 input / $6 output per 1M tokens
    Speed
    60.87 tok/s via DeepInfra

    Strengths

    • Ranks #3 with a 86.93 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens

    Considerations

    • 40% benchmark coverage
  4. 04
    DE
    DeepSeek
    LLMBoard Score
    86.78
    Speed
    45.48 tok/s via DeepSeek

    Strengths

    • Ranks #4 with a 86.78 LLMBoard Score
    • Open-weight model version
    • 1M maximum context tokens

    Considerations

    • 20% benchmark coverage
  5. 05
    ZA
    Zhipu AI
    LLMBoard Score
    84.28
    Price
    $0.08 input / $0.25 output per 1M tokens
    Speed
    74.28 tok/s via FriendliAI

    Strengths

    • Ranks #5 with a 84.28 LLMBoard Score
    • Open-weight model version
    • Lowest official input price among the top models

    Considerations

    • 20% benchmark coverage

Selection summary

Best AI Models for Open-Weight Use

Kimi K3 is the highest-ranked open-weight model at 89.45. 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.

Qwen3.8 Max
DeepSeek-V4-Pro
GLM 5.3 Flash
Open-model rank #1Kimi K3$3 input / $15 output per 1M tokens
Open-model rank #2GLM 5.3472.69 tok/s via FriendliAI
Open-model rank #3Qwen3.8 Max60.87 tok/s via DeepInfra