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
1281 models767 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 math (2026-06-25) Leaderboard

All tasks required; arithmetic mean: AMPS_Hard, integrals_with_game, math_comp, olympiad

Updated Sep 25, 2026

Models41
Model coverage41
Metricmath
EvidenceB

On this page

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

LiveBench math (2026-06-25) Ranking

Higher math ranks better on this benchmark.

30 of 41 rows
Columns

Show columns

Sort by
Rank
Model
math
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPGPT-6 AstraOpenAImath96.81 scorePercentile100.00%Participants41EvidenceBEvaluatedN/A
Rank02ModelOPGPT-5.6 SolOpenAImath96.20 scorePercentile97.50%Participants41EvidenceBEvaluatedN/A
Rank03ModelMEMuse Spark 1.3Metamath95.95 scorePercentile95.00%Participants41EvidenceBEvaluatedN/A
Rank04ModelOPGPT-5.5OpenAImath95.86 scorePercentile92.50%Participants41EvidenceBEvaluatedN/A
Rank05ModelXAGrok 4.7xAImath95.68 scorePercentile90.00%Participants41EvidenceBEvaluatedN/A
Rank06ModelDEDeepSeek-V4-Pro-0813DeepSeekmath95.09 scorePercentile87.50%Participants41EvidenceBEvaluatedN/A
Rank07ModelOPGPT-5.6 TerraOpenAImath94.91 scorePercentile85.00%Participants41EvidenceBEvaluatedN/A
Rank08ModelOPGPT-5.4OpenAImath94.15 scorePercentile82.50%Participants41EvidenceBEvaluatedN/A
Rank09ModelGOGemini 3.7 FlashGooglemath93.47 scorePercentile80.00%Participants41EvidenceBEvaluatedN/A
Rank10ModelOPGPT-5.2OpenAImath93.17 scorePercentile77.50%Participants41EvidenceBEvaluatedN/A
Rank11ModelXAGrok 4.6xAImath92.57 scorePercentile75.00%Participants41EvidenceBEvaluatedN/A
Rank12ModelGOGemini 3.8 FlashGooglemath91.56 scorePercentile72.50%Participants41EvidenceBEvaluatedN/A
Rank13ModelACQwen3.8 MaxAlibaba Cloud / Qwen Teammath91.31 scorePercentile70.00%Participants41EvidenceBEvaluatedN/A
Rank14ModelMEMuse Spark 1.2Metamath91.20 scorePercentile67.50%Participants41EvidenceBEvaluatedN/A
Rank15ModelGOGemini 3.1 ProGooglemath91.05 scorePercentile65.00%Participants41EvidenceBEvaluatedN/A
Rank16ModelOPGPT-5.4 nanoOpenAImath90.98 scorePercentile62.50%Participants41EvidenceBEvaluatedN/A
Rank17ModelXAGrok 4.5xAImath90.82 scorePercentile60.00%Participants41EvidenceBEvaluatedN/A
Rank18ModelZAGLM-5.2Zhipu AImath89.78 scorePercentile57.50%Participants41EvidenceBEvaluatedN/A
Rank19ModelOPGPT-5.2 CodexOpenAImath88.77 scorePercentile55.00%Participants41EvidenceBEvaluatedN/A
Rank20ModelNVNemotron 3 Ultra (550B A55B)NVIDIAmath88.66 scorePercentile52.50%Participants41EvidenceBEvaluatedN/A
Rank21ModelTMInklingThinking Machines Labmath88.36 scorePercentile50.00%Participants41EvidenceBEvaluatedN/A
Rank22ModelGOGemini 3.5 FlashGooglemath88.24 scorePercentile47.50%Participants41EvidenceBEvaluatedN/A
Rank23ModelZAGLM-5.3Zhipu AImath87.90 scorePercentile45.00%Participants41EvidenceBEvaluatedN/A
Rank24ModelDEDeepSeek-V4-Flash-Vision-ExpDeepSeekmath87.81 scorePercentile42.50%Participants41EvidenceBEvaluatedN/A
Rank25ModelOPGPT-5.6 LunaOpenAImath87.20 scorePercentile40.00%Participants41EvidenceBEvaluatedN/A
Rank26ModelMEMuse Spark 1.1Metamath87.14 scorePercentile37.50%Participants41EvidenceBEvaluatedN/A
Rank27ModelDEDeepSeek-V4-Flash-0731DeepSeekmath86.79 scorePercentile35.00%Participants41EvidenceBEvaluatedN/A
Rank28ModelGOGemini 3.6 FlashGooglemath86.40 scorePercentile32.50%Participants41EvidenceBEvaluatedN/A
Rank29ModelACQwen3.8-27BAlibaba Cloud / Qwen Teammath86.21 scorePercentile30.00%Participants41EvidenceBEvaluatedN/A
Rank30ModelACQwen3.8-Flash-NextAlibaba Cloud / Qwen Teammath85.82 scorePercentile27.50%Participants41EvidenceBEvaluatedN/A

LiveBench math (2026-06-25) Highlights

The leading models and scores on this benchmark.

LiveBench math (2026-06-25) Score Distribution

A closer view of the leading scores on this benchmark.

LiveBench math (2026-06-25)

The Top AI Models for LiveBench math (2026-06-25)

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

What is LiveBench math (2026-06-25)?

What LiveBench math (2026-06-25) measures and how its scores work.

All tasks required; arithmetic mean: AMPS_Hard, integrals_with_game, math_comp, olympiad

Scores are shown in score. This benchmark is verified and has an evidence level of B.

Family
livebench-math
Modality
text
Primary category
math
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
overall

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

FAQ

Common questions about LiveBench math (2026-06-25).

Which model scores highest on LiveBench math (2026-06-25)?

GPT-6 Astra is currently ranked first with 96.81 score.

What are the top three models on LiveBench math (2026-06-25)?

The current leaders are GPT-6 Astra (96.81 score), GPT-5.6 Sol (96.20 score), and Muse Spark 1.3 (95.95 score).

Which LiveBench math (2026-06-25) model has the lowest official input price?

DeepSeek-V4-Flash-Vision-Exp has the lowest matched official input price at $0.15 input / $0.60 output per 1M tokens.

Which models are fastest among LiveBench math (2026-06-25) results?

The fastest matched records are Gemini 3.6 Flash (188.24 tok/s via Google), Gemini 3.5 Flash-Lite (185.11 tok/s via Google), and Gemini 3.8 Flash (155.60 tok/s via Google).

Does the highest math 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 math (2026-06-25) measure?

All tasks required; arithmetic mean: AMPS_Hard, integrals_with_game, math_comp, olympiad

Is a higher math better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

41 model results are currently shown.

Does this benchmark affect the overall score?

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

Rank #1GPT-6 Astra96.81 score
Rank #2GPT-5.6 Sol96.20 score
Rank #3Muse Spark 1.395.95 score
Rank #4GPT-5.595.86 score

Ranking basisThis livebench math (2026-06-25) AI model leaderboard uses descending math in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    OP
    GPT-6 AstraOpenAI
    math
    96.81 score
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 25.98 tok/s via OpenAI

    Strengths

    • Ranks #1 of 41 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench math (2026-06-25), not total model capability
  2. 02
    OP
    GPT-5.6 SolOpenAI
    math
    96.20 score
    Price
    $4.0 input / $20 output per 1M tokens
    Speed
    Up to 35.30 tok/s via OpenAI

    Strengths

    • Ranks #2 of 41 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench math (2026-06-25), not total model capability
  3. 03
    ME
    Meta
    math
    95.95 score
    Price
    $1.3 input / $4.3 output per 1M tokens
    Speed
    Up to 4.64 tok/s via Meta Model API

    Strengths

    • Ranks #3 of 41 compared models
    • 95th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench math (2026-06-25), not total model capability
  4. 04
    OP
    OpenAI
    math
    95.86 score
    Price
    $5.0 input / $30 output per 1M tokens

    Strengths

    • Ranks #4 of 41 compared models
    • 93th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench math (2026-06-25), not total model capability
  5. 05
    XA
    xAI
    math
    95.68 score
    Price
    $2.0 input / $6.0 output per 1M tokens
    Speed
    Up to 5.32 tok/s via xAI

    Strengths

    • Ranks #5 of 41 compared models
    • 90th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures LiveBench math (2026-06-25), not total model capability

Selection summary

Best AI Models for LiveBench math (2026-06-25)

GPT-6 Astra currently leads LiveBench math (2026-06-25) with 96.81 score. 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.

Muse Spark 1.3
GPT-5.5
Grok 4.7
Benchmark rank #1GPT-6 Astra96.81 score · $10 input / $50 output per 1M tokens
Benchmark rank #2GPT-5.6 Sol96.20 score · $4.0 input / $20 output per 1M tokens
Benchmark rank #3Muse Spark 1.395.95 score · $1.3 input / $4.3 output per 1M tokens