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

LLM Leaderboard rankings and benchmark intelligence

LLM Leaderboard

Use the LLM Leaderboard to compare the best AI models across capability, price, speed and LLM benchmarks. Find the best LLM for coding, reasoning, math and everyday work with ranking data in one place.

View the LLM LeaderboardBrowse modelsCompare models
Model records
1,182
Leaderboards
23
Benchmarks
707
Last updated
2026-08-17

On this page

  • Featured rankings
  • Pricing & runtime
  • Benchmarks
  • Model types
  • Research tools

Live ranking snapshot

Current LLM leaderboard leaders

OverallLLMBoard score
01ANClaude Opus 5Anthropic96.502OPGPT-5.6-SolOpenAI95.303ANClaude Fable 5Anthropic95.204ANClaude MythosAnthropic93.305MAKimi K3Moonshot AI92.0
View all
Coding leader
ANClaude Sonnet 4.5
100.0Reasoning leader
ANClaude Opus 5
100.0Math leader
OPGPT-5.6-Sol
100.0Knowledge leader
SASakana Namazu
100.0Open models leader
MAKimi K3
92.0

Pricing & runtime

Compare LLM Leaderboard deployment signals

Price and runtime stay separate from capability scores, but they matter when choosing a model.
PricingLowest official input prices
USD / 1M
01Nova Micro$0.0402Nova Lite$0.0603Phi 4 Mini$0.0704Gemini 2.5 Flash Lite$0.1005Qwen2.5 Omni 7B$0.10
View all pricing
RuntimeFastest output speeds
tokens/s
01Llama 3.3 70B222002Llama 3.1 8B204703Min istral 3122204Llama 3.1 70B120405Mercury 21009
View all runtime
EfficiencyMore efficiency rankings
Explore
Capability vs. PriceImage PricingVideo PricingAudio PricingProvider Reliability

Benchmark library

Explore the LLM benchmarks behind the LLM Leaderboard

Open individual evaluations to see their raw model order, coverage and measurement scope.
View all benchmarks
classificationMTEB(eng, v2) Classification
253 models
01Conan-embedding-v292.2%02ingot-8b-r392.1%03voyage-3-m-exp90.8%04QZhou-Embedding90.7%05Jasper-Token-Compression-600M90.3%
View all results
physicsGPQA
239 models
01Claude Mythos Preview94.6%02GPT-5.6 Sol94.6%03Gemini 3.1 Pro94.3%04Claude Opus 4.794.2%05Claude Opus 4.893.6%
View all results
rerankingMTEB(eng, v2) Reranking
237 models
01Yuan-embedding-2.0-en53.3%02QZhou-Embedding51.8%03Qwen3-Embedding-8B51.6%04ingot-8b-r350.9%05Qwen3-Embedding-4B50.8%
View all results
clusteringMTEB(eng, v2) Clustering
213 models
01F2LLM-4B68.5%02F2LLM-1.7B64.1%03F2LLM-v2-14B63.5%04F2LLM-v2-8B62.8%05F2LLM-v2-4B62.0%
View all results

Browse by model type

Choose an LLM Leaderboard for every model type

Open the LLM Leaderboard that matches the task or output format you need.

Chat & LLM

10 rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision

Image

2 rankings

Image GenerationImage Editing

Video

3 rankings

Video GenerationImage to VideoVideo Editing

Audio

2 rankings

Text to SpeechSpeech to Text

Other Models

1 ranking

Embeddings

Research tools

Go beyond a single LLM Leaderboard position

Find the best LLM, compare alternatives, then check how the data is scored and maintained.
Model Directory

Filter the catalog by vendor, type, modality and price.

OpenCompare Models

Put capability, price and specifications side by side.

OpenScoring & Data

Read the scoring, coverage and model mapping rules.

Open

Start with the LLM leaderboard, then inspect the evidence

The overall AI model leaderboard is a practical starting point. Capability, price, runtime and benchmark pages keep each signal separate.

Explore the LLM leaderboard