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

Capability ranking

LLM Leaderboard

Use this LLM leaderboard to compare the current model ranking from aggregated benchmark evidence, coverage, official pricing and availability.

Updated 2026-09-08

On this page

  • Ranking
  • Overview
  • Leaders
  • Capability
  • Value
  • Composition
  • FAQ

Overall LLM Leaderboard Ranking

This leaderboard ranking combines aggregated capability scores, specifications, official pricing and featured benchmark results. Use Columns to show additional benchmarks.

30 of 305 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Score
Official input / 1M
Official output / 1M
Context
Released
Rank01ModelOPGPT-6-AstraOpenAILLMBoard Score98.89Official input / 1M$10Official output / 1M$50Context1.1MReleasedSep 4, 2026
Rank02ModelANClaude Fable 5.1AnthropicLLMBoard Score97.95Official input / 1M$10Official output / 1M$50Context1MReleasedSep 1, 2026
Rank03ModelANClaude Opus 5AnthropicLLMBoard Score93.24Official input / 1M$5Official output / 1M$25Context1MReleasedJul 24, 2026
Rank04ModelANClaude Fable 5AnthropicLLMBoard Score91.63Official input / 1M$10Official output / 1M$50Context1MReleasedJun 9, 2026
Rank05ModelANClaude MythosAnthropicLLMBoard Score91.30Official input / 1MN/AOfficial output / 1MN/AContextN/AReleasedN/A
Rank06ModelMEMuse Spark 1.3MetaLLMBoard Score90.82Official input / 1M$1.25Official output / 1M$4.25Context1MReleasedSep 2, 2026
Rank07ModelOPGPT-5.6-SolOpenAILLMBoard Score90.18Official input / 1M$4Official output / 1M$20Context1.1MReleasedJul 9, 2026
Rank08ModelMAKimi K3Moonshot AILLMBoard Score89.45Official input / 1M$3Official output / 1M$15Context1MReleasedJul 16, 2026
Rank09ModelZAGLM 5.3Zhipu AILLMBoard Score88.97Official input / 1M$1.4Official output / 1M$4.4Context1MReleasedAug 14, 2026
Rank10ModelACQwen3.8 MaxAlibaba Cloud / Qwen TeamLLMBoard Score86.93Official input / 1M$2Official output / 1M$6Context1MReleasedAug 2, 2026
Rank11ModelDEDeepSeek-V4-ProDeepSeekLLMBoard Score86.78Official input / 1MN/AOfficial output / 1MN/AContext1MReleasedAug 13, 2026
Rank12ModelGOGemini 3.8 FlashGoogleLLMBoard Score86.74Official input / 1M$0.75Official output / 1M$3.75Context1MReleasedSep 2, 2026
Rank13ModelANClaude Opus 4.8AnthropicLLMBoard Score85.39Official input / 1M$5Official output / 1M$25Context1MReleasedMay 28, 2026
Rank14ModelMEMuse Spark 1.1MetaLLMBoard Score85.17Official input / 1M$1.25Official output / 1M$4.25Context1MReleasedJul 9, 2026
Rank15ModelZAGLM 5.3 FlashZhipu AILLMBoard Score84.28Official input / 1M$0.075Official output / 1M$0.25Context1MReleasedAug 26, 2026
Rank16ModelTEHy4TencentLLMBoard Score83.71Official input / 1MN/AOfficial output / 1MN/AContextN/AReleasedAug 28, 2026
Rank17ModelOPGPT-5.6-TerraOpenAILLMBoard Score83.21Official input / 1M$2Official output / 1M$12Context1.1MReleasedJul 9, 2026
Rank18ModelGOGemini 3.7 FlashGoogleLLMBoard Score82.79Official input / 1M$0.75Official output / 1M$3.75Context1MReleasedAug 13, 2026
Rank19ModelANClaude Opus 4.7AnthropicLLMBoard Score82.26Official input / 1M$5Official output / 1M$25Context1MReleasedApr 16, 2026
Rank20ModelOPGPT-5.5OpenAILLMBoard Score81.73Official input / 1M$5Official output / 1M$30Context1.1MReleasedApr 23, 2026
Rank21ModelACQwen3.8 Flash NextAlibaba Cloud / Qwen TeamLLMBoard Score81.44Official input / 1MN/AOfficial output / 1MN/AContextN/AReleasedAug 26, 2026
Rank22ModelACQwen3.8 FlashAlibaba Cloud / Qwen TeamLLMBoard Score81.35Official input / 1M$0.15Official output / 1M$0.47Context1MReleasedAug 26, 2026
Rank23ModelANClaude Sonnet 5AnthropicLLMBoard Score80.16Official input / 1M$2Official output / 1M$10Context1MReleasedJun 30, 2026
Rank24ModelMEMuse Spark 1.2MetaLLMBoard Score78.98Official input / 1M$1.25Official output / 1M$4.25Context1MReleasedAug 5, 2026
Rank25ModelANClaude Opus 4.6AnthropicLLMBoard Score78.18Official input / 1M$5Official output / 1M$25Context1MReleasedFeb 5, 2026
Rank26ModelZAGLM 5.2Zhipu AILLMBoard Score77.02Official input / 1M$1.4Official output / 1M$4.4Context1MReleasedJun 16, 2026
Rank27ModelBYSeed 2.1 ProByteDanceLLMBoard Score76.86Official input / 1MN/AOfficial output / 1MN/AContextN/AReleasedJun 24, 2026
Rank28ModelXAGrok 4.6xAILLMBoard Score76.81Official input / 1M$2Official output / 1M$6Context500KReleasedAug 12, 2026
Rank29ModelGOGemini 3.5 FlashGoogleLLMBoard Score76.67Official input / 1M$1.5Official output / 1M$9Context1MReleasedMay 19, 2026
Rank30ModelDEDeepSeek-V4-FlashDeepSeekLLMBoard Score76.66Official input / 1M$0.14Official output / 1M$0.28Context1MReleasedAug 21, 2026

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 overall leaderboard ranking and its supporting benchmark coverage.

Ranked models305
Vendors33
Open-weight models166
Official prices132

GPT-6-Astra leads this page at 98.89, 0.94 points ahead of Claude Fable 5.1.

Kimi K3 is the highest-ranked open-weight option at #8. Nova Micro has the lowest official input price among ranked models.

Overall Leaderboard Leaders

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

Top overall models

Overall Benchmark Profile

Compare each leaderboard leader's overall score with its weakest measured benchmark capability.

ModelReasoningKnowledgeMathCodingInstruction
GPT-6-AstraOpenAI100.00N/AN/A94.72N/A
Claude Fable 5.1AnthropicN/AN/AN/AN/AN/A
Claude Opus 5AnthropicN/A82.60N/A84.58N/A
Claude Fable 5AnthropicN/A98.53N/A91.86N/A
Claude MythosAnthropicN/A99.27N/A98.82N/A
43.5853.7563.9174.0884.2556.0563.9371.8079.6887.56Weakest categoryLLMBoard Overall Score
17 models with comparable dataOpen a model by selecting its logo

Capability at each price point

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

020406080100$0.05$0.1$0.2$0.5$1.0$2.0$5.0$10LLMBoard ScoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier132 models with official PAYG prices

Overall Leaderboard Composition

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

Top-model vendor mix

25 models
Anthropic8
OpenAI4
Meta3
Alibaba Cloud / Qwen Team3
Zhipu AI2
Google2
Moonshot AI1
DeepSeek1

Access model

Open weights
8
Closed weights
17
Official price available
21

About this leaderboard

Common questions about the LLM Leaderboard leaderboard, benchmark evidence and ranking method.

What is the best model on LLM Leaderboard?

GPT-6-Astra is currently ranked first with a overall score of 98.89.

Which three AI models lead this capability ranking?

The current leaders are GPT-6-Astra (98.89 LLMBoard Score), Claude Fable 5.1 (97.95 LLMBoard Score), and Claude Opus 5 (93.24 LLMBoard Score).

Which ranked model has the lowest official input price?

Nova Micro has the lowest current official input price among ranked models at $0.04 per 1M tokens.

Which ranked models have the highest measured output speed?

No matched runtime record is currently available.

Which open-weight model ranks highest?

Kimi K3 is the highest-ranked open-weight model at rank #8.

Which model offers the longest context in this ranking?

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

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 305 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.

Top overall modelGPT-6-Astra98.89 overall score
Best open-weight modelKimi K3Rank #8
Lowest official inputNova Micro$0.04 / 1M
Largest contextLlama 4 Scout10M tokens