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
1367 models808 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

Best AI for Math

Use this math model leaderboard to compare the current ranking from the LLMBoard Math Score after applying benchmark evidence requirements.

Updated 2026-10-22

On this page

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

Math Model Leaderboard Ranking

This leaderboard ranking orders models by their LLMBoard Math Score aggregated from eligible benchmark evidence.

30 of 129 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Math Score
Official input / 1M
Official output / 1M
License
Rank01ModelOPGPT-5.2-ProOpenAILLMBoard Math Score99.18Official input / 1M$21Official output / 1M$168LicenseClosed
Rank02ModelXAGrok 4 HeavyxAILLMBoard Math Score99.18Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank03ModelOPGPT-5.6-SolOpenAILLMBoard Math Score97.62Official input / 1M$4Official output / 1M$20LicenseClosed
Rank04ModelXIMiMo V2.5 ProXiaomiLLMBoard Math Score92.85Official input / 1M$0.435Official output / 1M$0.87LicenseOpen
Rank05ModelDEDeepSeek-V3.2DeepSeekLLMBoard Math Score89.03Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank06ModelOPGPT-5.6-TerraOpenAILLMBoard Math Score88.54Official input / 1M$2Official output / 1M$12LicenseClosed
Rank07ModelOPGPT-5.2OpenAILLMBoard Math Score86.01Official input / 1M$1.75Official output / 1M$14LicenseClosed
Rank08ModelGOGemini 2.0 Flash LiteGoogleLLMBoard Math Score85.95Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank09ModelACQwen2.5 32BAlibaba Cloud / Qwen TeamLLMBoard Math Score81.67Official input / 1M$0.70Official output / 1M$2.8LicenseOpen
Rank10ModelZAGLM 5.2Zhipu AILLMBoard Math Score81.25Official input / 1M$1.2Official output / 1M$4.18LicenseOpen
Rank11ModelOPGPT-5.4OpenAILLMBoard Math Score81.10Official input / 1M$2.5Official output / 1M$15LicenseClosed
Rank12ModelANClaude Sonnet 3.5AnthropicLLMBoard Math Score79.87Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank13ModelZAGLM 4.5 AirZhipu AILLMBoard Math Score77.94Official input / 1M$0.1195Official output / 1M$0.8964LicenseOpen
Rank14ModelZAGLM 4.5Zhipu AILLMBoard Math Score77.40Official input / 1M$0.60Official output / 1M$2.2LicenseOpen
Rank15ModelOPGPT-5.5OpenAILLMBoard Math Score76.49Official input / 1M$5Official output / 1M$30LicenseClosed
Rank16ModelSTStep 3.5 FlashStepFunLLMBoard Math Score75.58Official input / 1M$0.10Official output / 1M$0.30LicenseOpen
Rank17ModelMELlama 3.1 405BMetaLLMBoard Math Score75.03Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank18ModelNVNemotron 3 UltraNVIDIALLMBoard Math Score75.00Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank19ModelXAGrok 4xAILLMBoard Math Score73.80Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank20ModelSASarvam 105BSarvam AILLMBoard Math Score73.72Official input / 1M$0.1579Official output / 1M$0.6316LicenseOpen
Rank21ModelACQwen2.5 14BAlibaba Cloud / Qwen TeamLLMBoard Math Score73.13Official input / 1M$0.35Official output / 1M$1.4LicenseOpen
Rank22ModelACQwen3.7 PlusAlibaba Cloud / Qwen TeamLLMBoard Math Score72.03Official input / 1M$0.40Official output / 1M$1.6LicenseClosed
Rank23ModelGOGemma 3 27BGoogleLLMBoard Math Score71.26Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank24ModelGOGemini 2.0 FlashGoogleLLMBoard Math Score71.08Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank25ModelTMInklingThinking Machines LabLLMBoard Math Score69.97Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank26ModelDEDeepSeek-V2.5DeepSeekLLMBoard Math Score69.36Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank27ModelNVNemotron 3 SuperNVIDIALLMBoard Math Score69.23Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank28ModelGOGemini 1.5 ProGoogleLLMBoard Math Score66.87Official input / 1MN/AOfficial output / 1MN/ALicenseClosed
Rank29ModelMAKimi K2.5Moonshot AILLMBoard Math Score66.02Official input / 1MN/AOfficial output / 1MN/ALicenseOpen
Rank30ModelXAGrok 4 FastxAILLMBoard Math Score65.50Official input / 1MN/AOfficial output / 1MN/ALicenseClosed

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 math leaderboard ranking and its supporting benchmark coverage.

Ranked models129
Vendors24
Open-weight models84
Official prices46

GPT-5.2-Pro leads this page at 99.18, 0.00 points ahead of Grok 4 Heavy.

MiMo V2.5 Pro is the highest-ranked open-weight option at #4. Nova Micro has the lowest official input price among ranked models.

Math Leaderboard Leaders

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

Top math models

Math Benchmark Profile

Compare math benchmark strength with each model's broader capability score and leaderboard position.

ModelReasoningKnowledgeMathCodingInstruction
GPT-5.2-ProOpenAI76.90N/A99.18N/AN/A
Grok 4 HeavyxAIN/AN/A99.18N/AN/A
GPT-5.6-SolOpenAI99.0173.1397.6281.5081.02
MiMo V2.5 ProXiaomi81.0661.7992.8552.2891.51
DeepSeek-V3.2DeepSeek76.0766.9889.0353.1456.90
32.1950.4668.7387.00105.27-6.9518.2443.4268.6093.79LLMBoard Math ScoreLLMBoard Overall Score
80 models with comparable dataOpen a model by selecting its logo

Capability at each price point

Official vendor API prices plotted against the math 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 Math ScoreOfficial API price blend (8:1 input/output), USD / 1M
Efficient frontier46 models with official PAYG prices

Math Leaderboard Composition

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

Top-model vendor mix

25 models
OpenAI6
Google3
Alibaba Cloud / Qwen Team3
Zhipu AI3
xAI2
Xiaomi1
DeepSeek1
Anthropic1

Access model

Open weights
12
Closed weights
13
Official price available
15

The Top AI Models for Math

A data-backed look at the first five models in this math leaderboard ranking, including benchmark context, price and output speed where available.

About this leaderboard

Common questions about the Best AI for Math leaderboard, benchmark evidence and ranking method.

What is the best model on Best AI for Math?

GPT-5.2-Pro is currently ranked first with a math score of 99.18.

Which three AI models lead this capability ranking?

The current leaders are GPT-5.2-Pro (99.18 LLMBoard Math Score), Grok 4 Heavy (99.18 LLMBoard Math Score), and GPT-5.6-Sol (97.62 LLMBoard Math 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?

The fastest matched records are Llama 4 Scout (776.10 tok/s via Groq), Llama 4 Maverick (638.70 tok/s via Sambanova), and GPT-5-Nano (500.00 tok/s via OpenAI).

Which open-weight model ranks highest?

MiMo V2.5 Pro is the highest-ranked open-weight model at rank #4.

AA Omniscience Accuracy59.40%GPT-5.6-Sol77 compared models
AA CritPt32.29%GPT-5.6-Sol77 compared models
AA HLE Text No Tools49.49%GPT-5.6-Sol77 compared models
AA GPQA Diamond94.14%GPT-5.6-Sol77 compared models
AA LCR v1.184.33%GPT-5.572 compared models
AA IFBench81.36%Nemotron 3 Ultra70 compared models
AA AIME 202596.67%DeepSeek-V3.245 compared models
AA SciCode Subtasks57.75%GPT-5.6-Sol32 compared models
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 129 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 math modelGPT-5.2-Pro99.18 math score
Best open-weight modelMiMo V2.5 ProRank #4
Lowest official inputNova Micro$0.04 / 1M
Largest contextLlama 4 Scout10M tokens

Ranking basisThis math AI model leaderboard uses the math capability score shown on this page. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    OP
    GPT-5.2-ProOpenAI
    LLMBoard Math Score
    99.18
    Price
    $21 input / $168 output per 1M tokens
    Speed
    25.00 tok/s via OpenAI

    Strengths

    • Ranks #1 with a 99.18 LLMBoard Math Score
    • 400K maximum context tokens

    Considerations

    • Provisional score with 40% benchmark coverage
    • Weights are not marked as open
  2. 02
    XA
    Grok 4 HeavyxAI
    LLMBoard Math Score
    99.18

    Strengths

    • Ranks #2 with a 99.18 LLMBoard Math Score

    Considerations

    • Provisional score with 20% benchmark coverage
    • Weights are not marked as open
  3. 03
    OP
    OpenAI
    LLMBoard Math Score
    97.62
    Price
    $4 input / $20 output per 1M tokens
    Speed
    25.46 tok/s via OpenAI

    Strengths

    • Ranks #3 with a 97.62 LLMBoard Math Score
    • 1.1M maximum context tokens

    Considerations

    • Weights are not marked as open
  4. 04
    XI
    Xiaomi
    LLMBoard Math Score
    92.85
    Price
    $0.44 input / $0.87 output per 1M tokens

    Strengths

    • Ranks #4 with a 92.85 LLMBoard Math Score
    • Open-weight model version
    • Lowest official input price among the top models
  5. 05
    DE
    DeepSeek
    LLMBoard Math Score
    89.03
    Speed
    30.00 tok/s via DeepSeek

    Strengths

    • Ranks #5 with a 89.03 LLMBoard Math Score
    • 131K maximum context tokens

    Considerations

    • Provisional score with 100% benchmark coverage
    • Weights are not marked as open

Selection summary

Best AI Models for Math

GPT-5.2-Pro is currently the best-ranked LLM for math with a 99.18 math score. The score is a relative ranking signal, so price, speed, context and evidence coverage should still be checked separately.

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-5.6-Sol
MiMo V2.5 Pro
DeepSeek-V3.2
Capability rank #1GPT-5.2-Pro25.00 tok/s via OpenAI
Capability rank #2Grok 4 Heavy99.18
Capability rank #3GPT-5.6-Sol25.46 tok/s via OpenAI