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

math benchmark

LiveBench Leaderboard

LiveBench is a benchmark with monthly releases of new questions based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses, covering math, coding, reasoning, language, instruction following, and data analysis.

Updated Sep 5, 2026

Models38
Model coverage38
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

LiveBench Ranking

Higher score ranks better on this benchmark.

30 of 38 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPo3-miniOpenAIScore84.60%Percentile100.00%Participants38EvidenceCEvaluatedSep 8, 2026
Rank02ModelOPGPT-5.5OpenAIScore80.71%Percentile97.30%Participants38EvidenceBEvaluatedSep 8, 2026
Rank03ModelOPGPT-5.4OpenAIScore80.28%Percentile94.59%Participants38EvidenceBEvaluatedSep 8, 2026
Rank04ModelGOGemini 3.1 ProGoogleScore79.93%Percentile91.89%Participants38EvidenceBEvaluatedSep 8, 2026
Rank05ModelANClaude Fable 5AnthropicScore78.31%Percentile89.19%Participants38EvidenceBEvaluatedSep 8, 2026
Rank06ModelANClaude Opus 4.8AnthropicScore77.22%Percentile86.49%Participants38EvidenceBEvaluatedSep 8, 2026
Rank07ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamScore77.10%Percentile83.78%Participants38EvidenceCEvaluatedSep 8, 2026
Rank08ModelANClaude Opus 4.7AnthropicScore76.91%Percentile81.08%Participants38EvidenceBEvaluatedSep 8, 2026
Rank09ModelMAKimi K2 InstructMoonshot AIScore76.40%Percentile78.38%Participants38EvidenceCEvaluatedSep 8, 2026
Rank10ModelMAKimi K2-Instruct-0905Moonshot AIScore76.40%Percentile75.68%Participants38EvidenceCEvaluatedSep 8, 2026
Rank11ModelANClaude Opus 4.6AnthropicScore76.33%Percentile72.97%Participants38EvidenceBEvaluatedSep 8, 2026
Rank12ModelANClaude Opus 4.5AnthropicScore75.96%Percentile70.27%Participants38EvidenceBEvaluatedSep 8, 2026
Rank13ModelANClaude Sonnet 4.6AnthropicScore75.47%Percentile67.57%Participants38EvidenceBEvaluatedSep 8, 2026
Rank14ModelGOGemini 3.5 FlashGoogleScore75.02%Percentile64.86%Participants38EvidenceBEvaluatedSep 8, 2026
Rank15ModelACQwen3 32BAlibaba Cloud / Qwen TeamScore74.90%Percentile62.16%Participants38EvidenceCEvaluatedSep 8, 2026
Rank16ModelOPGPT-5.2OpenAIScore74.84%Percentile59.46%Participants38EvidenceBEvaluatedSep 8, 2026
Rank17ModelOPGPT-5.2 CodexOpenAIScore74.30%Percentile56.76%Participants38EvidenceBEvaluatedSep 8, 2026
Rank18ModelACQwen3 30B A3BAlibaba Cloud / Qwen TeamScore74.30%Percentile54.05%Participants38EvidenceCEvaluatedSep 8, 2026
Rank19ModelACQwen3.7 MaxAlibaba Cloud / Qwen TeamScore74.29%Percentile51.35%Participants38EvidenceBEvaluatedSep 8, 2026
Rank20ModelDEDeepSeek-V4-Pro-MaxDeepSeekScore73.58%Percentile48.65%Participants38EvidenceBEvaluatedSep 8, 2026
Rank21ModelGOGemini 3 ProGoogleScore73.39%Percentile45.95%Participants38EvidenceBEvaluatedSep 8, 2026
Rank22ModelACQwQ-32BAlibaba Cloud / Qwen TeamScore73.10%Percentile43.24%Participants38EvidenceCEvaluatedSep 8, 2026
Rank23ModelOPGPT-5.3 CodexOpenAIScore72.76%Percentile40.54%Participants38EvidenceBEvaluatedSep 8, 2026
Rank24ModelGOGemini 3 FlashGoogleScore72.40%Percentile37.84%Participants38EvidenceBEvaluatedSep 8, 2026
Rank25ModelMAKimi K2.6Moonshot AIScore72.17%Percentile35.14%Participants38EvidenceBEvaluatedSep 8, 2026
Rank26ModelOPGPT-5.1 HighOpenAIScore72.04%Percentile32.43%Participants38EvidenceBEvaluatedSep 8, 2026
Rank27ModelMAKimi K2.7 CodeMoonshot AIScore71.89%Percentile29.73%Participants38EvidenceBEvaluatedSep 8, 2026
Rank28ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamScore70.85%Percentile27.03%Participants38EvidenceBEvaluatedSep 8, 2026
Rank29ModelZAGLM-5.1Zhipu AIScore70.18%Percentile24.32%Participants38EvidenceBEvaluatedSep 8, 2026
Rank30ModelOPGPT-5.4 nanoOpenAIScore70.13%Percentile21.62%Participants38EvidenceBEvaluatedSep 8, 2026

LiveBench Highlights

The leading models and scores on this benchmark.

LiveBench Score Distribution

A closer view of the leading scores on this benchmark.

LiveBench

The Top AI Models for LiveBench

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

What is LiveBench?

What LiveBench measures and how its scores work.

LiveBench is a contamination-limited LLM benchmark comprising tasks across math, coding, reasoning, language, instruction following, and data analysis.

It measures performance on tasks with verifiable, objective ground-truth answers, reported as Score in ratio units.

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
No
Evaluation key
overall

LLM Stats. 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 84.60%.

What are the top three models on LiveBench?

The current leaders are o3-mini (84.60%), GPT-5.5 (80.71%), and GPT-5.4 (80.28%).

Which LiveBench model has the lowest official input price?

Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.

Which models are fastest among LiveBench results?

The fastest matched records are Gemini 3.5 Flash (210.94 tok/s via Google), GPT-5.5 (134.94 tok/s via OpenAI), and Gemini 3 Flash (124.32 tok/s via Google).

Does the highest score result prove overall model quality?

No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.

What does LiveBench measure?

It measures performance on tasks with verifiable, objective ground-truth answers, reported as Score in ratio units.

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?

No. This benchmark is shown for reference but does not contribute to the overall score.

Rank #1o3-mini84.60%
Rank #2GPT-5.580.71%
Rank #3GPT-5.480.28%
Rank #4Gemini 3.1 Pro79.93%

Ranking basisThis livebench AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    OP
    o3-miniOpenAI
    Score
    84.60%
    Price
    $1.1 input / $4.4 output per 1M tokens
    Speed
    Up to 115.00 tok/s via Azure

    Strengths

    • Ranks #1 of 38 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures LiveBench, not total model capability
  2. 02
    OP
    GPT-5.5OpenAI
    Score
    80.71%
    Price
    $5.0 input / $30 output per 1M tokens
    Speed
    Up to 134.94 tok/s via OpenAI

    Strengths

    • Ranks #2 of 38 compared models
    • 97th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench, not total model capability
  3. 03
    OP
    OpenAI
    Score
    80.28%
    Price
    $2.5 input / $15 output per 1M tokens
    Speed
    Up to 50.00 tok/s via OpenAI

    Strengths

    • Ranks #3 of 38 compared models
    • 95th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench, not total model capability
  4. 04
    GO
    Google
    Score
    79.93%
    Price
    $2.0 input / $12 output per 1M tokens
    Speed
    Up to 43.79 tok/s via Google

    Strengths

    • Ranks #4 of 38 compared models
    • 92th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench, not total model capability
  5. 05
    AN
    Anthropic
    Score
    78.31%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 43.18 tok/s via Anthropic

    Strengths

    • Ranks #5 of 38 compared models
    • 89th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench, not total model capability

Selection summary

Best AI Models for LiveBench

o3-mini currently leads LiveBench with 84.60%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.

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.

GPT-5.4
Gemini 3.1 Pro
Claude Fable 5
Benchmark rank #1o3-mini84.60% · $1.1 input / $4.4 output per 1M tokens
Benchmark rank #2GPT-5.580.71% · $5.0 input / $30 output per 1M tokens
Benchmark rank #3GPT-5.480.28% · $2.5 input / $15 output per 1M tokens