llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
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

math benchmark

LiveBench

LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

Updated Aug 11, 2026

Models38
Model coverage38
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

LiveBench Ranking

Higher score ranks better on this benchmark.

38 rows
Columns

Show columns

01OPo3-miniOpenAI84.6%100.0%38CAug 11, 2026
02OPGPT-5.5OpenAI80.7%97.3%38BAug 11, 2026
03OPGPT-5.4OpenAI80.3%94.6%38BAug 11, 2026
04GOGemini 3.1 ProGoogle79.9%91.9%38BAug 11, 2026
05ANClaude Fable 5Anthropic78.3%89.2%38BAug 11, 2026
06ANClaude Opus 4.8Anthropic77.2%86.5%38BAug 11, 2026
07ACQwen3 235B A22BAlibaba Cloud / Qwen Team77.1%83.8%38CAug 11, 2026
08ANClaude Opus 4.7Anthropic76.9%81.1%38BAug 11, 2026
09MAKimi K2 InstructMoonshot AI76.4%78.4%38CAug 11, 2026
10MAKimi K2-Instruct-0905Moonshot AI76.4%75.7%38CAug 11, 2026
11ANClaude Opus 4.6Anthropic76.3%73.0%38BAug 11, 2026
12ANClaude Opus 4.5Anthropic76.0%70.3%38BAug 11, 2026
13ANClaude Sonnet 4.6Anthropic75.5%67.6%38BAug 11, 2026
14GOGemini 3.5 FlashGoogle75.0%64.9%38BAug 11, 2026
15ACQwen3 32BAlibaba Cloud / Qwen Team74.9%62.2%38CAug 11, 2026
16OPGPT-5.2OpenAI74.8%59.5%38BAug 11, 2026
17OPGPT-5.2 CodexOpenAI74.3%56.8%38BAug 11, 2026
18ACQwen3 30B A3BAlibaba Cloud / Qwen Team74.3%54.0%38CAug 11, 2026
19ACQwen3.7 MaxAlibaba Cloud / Qwen Team74.3%51.4%38BAug 11, 2026
20DEDeepSeek-V4-Pro-MaxDeepSeek73.6%48.6%38BAug 11, 2026
21GOGemini 3 ProGoogle73.4%46.0%38BAug 11, 2026
22ACQwQ-32BAlibaba Cloud / Qwen Team73.1%43.2%38CAug 11, 2026
23OPGPT-5.3 CodexOpenAI72.8%40.5%38BAug 11, 2026
24GOGemini 3 FlashGoogle72.4%37.8%38BAug 11, 2026
25MAKimi K2.6Moonshot AI72.2%35.1%38BAug 11, 2026
26OPGPT-5.1 HighOpenAI72.0%32.4%38BAug 11, 2026
27MAKimi K2.7 CodeMoonshot AI71.9%29.7%38BAug 11, 2026
28ACQwen3.6 PlusAlibaba Cloud / Qwen Team70.9%27.0%38BAug 11, 2026
29ZAGLM-5.1Zhipu AI70.2%24.3%38BAug 11, 2026
30OPGPT-5.4 nanoOpenAI70.1%21.6%38BAug 11, 2026
31MIMiniMax M3MiniMax70.0%18.9%38BAug 11, 2026
32MAKimi K2.5Moonshot AI69.1%16.2%38BAug 11, 2026
33OPo1OpenAI67.0%13.5%38CAug 11, 2026
34OPo1-previewOpenAI52.3%10.8%38CAug 11, 2026
35ACQwen2.5 72B InstructAlibaba Cloud / Qwen Team52.3%8.1%38CAug 11, 2026
36MIPhi 4Microsoft47.6%5.4%38CAug 11, 2026
37ACQwen2.5 7B InstructAlibaba Cloud / Qwen Team35.9%2.7%38CAug 11, 2026
38ACQwen2.5-Omni-7BAlibaba Cloud / Qwen Team29.6%0.0%38CAug 11, 2026

LiveBench Score Distribution

A closer view of the leading scores on this benchmark.

LiveBench

LiveBench Highlights

The leading models and scores on this benchmark.

Rank #1o3-mini84.6%Rank #2GPT-5.580.7%Rank #3GPT-5.480.3%Rank #4Gemini 3.1 Pro79.9%

What is LiveBench?

What LiveBench measures and how its scores work.

LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
LiveBench
Modality
text
Primary category
math
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
livebench|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about LiveBench.

Which model scores highest on LiveBench?

o3-mini is currently ranked first with 84.6%.

What does LiveBench measure?

LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

38 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.