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

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 2026-08-17

On this page

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

Math Model Leaderboard Ranking

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

30 of 108 rows
Columns

Show columns

Sort by
Rank
Model
LLMBoard Math Score
Official input / 1M
Official output / 1M
License
Rank01ModelOPGPT-5.2-ProOpenAILLMBoard Math Score99.1Official input / 1M$21Official output / 1M$168LicenseClosed weights
Rank02ModelXAGrok 4 HeavyxAILLMBoard Math Score99.1Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank03ModelGOGemini 2.0 FlashGoogleLLMBoard Math Score97.2Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank04ModelACQwen3.7 MaxAlibaba Cloud / Qwen TeamLLMBoard Math Score93.4Official input / 1M$2.5Official output / 1M$7.5LicenseClosed weights
Rank05ModelXIMiMo V2.5 ProXiaomiLLMBoard Math Score92.8Official input / 1M$0.435Official output / 1M$0.87LicenseOpen weights
Rank06ModelZAGLM 4.5Zhipu AILLMBoard Math Score90.0Official input / 1M$0.60Official output / 1M$2.2LicenseOpen weights
Rank07ModelOPGPT-5.2OpenAILLMBoard Math Score90.0Official input / 1M$1.75Official output / 1M$14LicenseClosed weights
Rank08ModelZAGLM 5.2Zhipu AILLMBoard Math Score89.9Official input / 1M$1.4Official output / 1M$4.4LicenseOpen weights
Rank09ModelGOGemma 3 27BGoogleLLMBoard Math Score89.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank10ModelDEDeepSeek-V3.2DeepSeekLLMBoard Math Score88.5Official input / 1M$0.14Official output / 1M$0.28LicenseClosed weights
Rank11ModelZAGLM 4.5 AirZhipu AILLMBoard Math Score86.5Official input / 1M$0.20Official output / 1M$1.1LicenseOpen weights
Rank12ModelGOGemini 2.0 Flash LiteGoogleLLMBoard Math Score86.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank13ModelACQwen2.5 32BAlibaba Cloud / Qwen TeamLLMBoard Math Score81.7Official input / 1M$0.70Official output / 1M$2.8LicenseClosed weights
Rank14ModelACQwen2.5 72BAlibaba Cloud / Qwen TeamLLMBoard Math Score80.1Official input / 1M$1.4Official output / 1M$5.6LicenseClosed weights
Rank15ModelANClaude Sonnet 3.5AnthropicLLMBoard Math Score79.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank16ModelMELlama 3.1 405BMetaLLMBoard Math Score75.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank17ModelGOGemma 3 12BGoogleLLMBoard Math Score74.8Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank18ModelSASarvam 105BSarvam AILLMBoard Math Score73.4Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank19ModelSTStep 3.5 FlashStepFunLLMBoard Math Score73.3Official input / 1M$0.10Official output / 1M$0.30LicenseOpen weights
Rank20ModelMAKimi K2.6Moonshot AILLMBoard Math Score73.1Official input / 1M$0.95Official output / 1M$4LicenseOpen weights
Rank21ModelACQwen2.5 14BAlibaba Cloud / Qwen TeamLLMBoard Math Score73.1Official input / 1M$0.35Official output / 1M$1.4LicenseClosed weights
Rank22ModelXAGrok 4xAILLMBoard Math Score72.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank23ModelAMNova ProAmazonLLMBoard Math Score69.9Official input / 1M$0.80Official output / 1M$3.2LicenseClosed weights
Rank24ModelDEDeepSeek-V2.5DeepSeekLLMBoard Math Score69.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank25ModelACQwen3.7 PlusAlibaba Cloud / Qwen TeamLLMBoard Math Score69.3Official input / 1M$0.50Official output / 1M$3LicenseClosed weights
Rank26ModelACQwen3.6 PlusAlibaba Cloud / Qwen TeamLLMBoard Math Score69.1Official input / 1M$0.50Official output / 1M$3LicenseClosed weights
Rank27ModelNVNemotron 3 SuperNVIDIALLMBoard Math Score68.9Official input / 1M$0.20Official output / 1M$0.80LicenseOpen weights
Rank28ModelGOGemini 1.5 ProGoogleLLMBoard Math Score66.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank29ModelMAKimi K2.5Moonshot AILLMBoard Math Score66.7Official input / 1M$0.60Official output / 1M$3LicenseOpen weights
Rank30ModelMAKimi K2 ThinkingMoonshot AILLMBoard Math Score65.6Official input / 1M$0.60Official output / 1M$2.5LicenseClosed weights
Rank31ModelXAGrok 4 FastxAILLMBoard Math Score65.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank32ModelOPGPT-5.1OpenAILLMBoard Math Score64.0Official input / 1M$1.25Official output / 1M$10LicenseClosed weights
Rank33ModelOPGPT-5.1-InstantOpenAILLMBoard Math Score64.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank34ModelZAGLM 5.1Zhipu AILLMBoard Math Score63.9Official input / 1M$1.4Official output / 1M$4.4LicenseOpen weights
Rank35ModelOPo3 miniOpenAILLMBoard Math Score63.8Official input / 1M$1.1Official output / 1M$4.4LicenseClosed weights
Rank36ModelAMNova LiteAmazonLLMBoard Math Score63.7Official input / 1M$0.06Official output / 1M$0.24LicenseClosed weights
Rank37ModelACQwen3 235B A22B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score63.6Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank38ModelZAGLM 4.7Zhipu AILLMBoard Math Score59.6Official input / 1M$0.60Official output / 1M$2.2LicenseOpen weights
Rank39ModelSASarvam 30BSarvam AILLMBoard Math Score59.1Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank40ModelACQwen2.5 7BAlibaba Cloud / Qwen TeamLLMBoard Math Score58.4Official input / 1M$0.175Official output / 1M$0.70LicenseClosed weights
Rank41ModelMIMAI Thinking 1MicrosoftLLMBoard Math Score57.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank42ModelOPo1OpenAILLMBoard Math Score57.2Official input / 1M$15Official output / 1M$60LicenseClosed weights
Rank43ModelXIMiMo V2 FlashXiaomiLLMBoard Math Score57.1Official input / 1M$0.14Official output / 1M$0.28LicenseOpen weights
Rank44ModelNVNemotron Nano 9BNVIDIALLMBoard Math Score56.9Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank45ModelANClaude Opus 3AnthropicLLMBoard Math Score55.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank46ModelACQwen3 VL 235B A22B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score54.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank47ModelGOGemini 1.5 FlashGoogleLLMBoard Math Score52.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank48ModelNVLlama 3.1 Nemotron Ultra 253BNVIDIALLMBoard Math Score51.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank49ModelGOGemma 3 4BGoogleLLMBoard Math Score51.8Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank50ModelMIMiniMax M1 80KMiniMaxLLMBoard Math Score51.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank51ModelAMNova MicroAmazonLLMBoard Math Score50.7Official input / 1M$0.035Official output / 1M$0.14LicenseClosed weights
Rank52ModelMELongCat Flash ThinkingMeituanLLMBoard Math Score50.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank53ModelOPGPT-4.5OpenAILLMBoard Math Score48.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank54ModelMAKimi k1.5Moonshot AILLMBoard Math Score47.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank55ModelACQwen3.5 397B A17BAlibaba Cloud / Qwen TeamLLMBoard Math Score47.5Official input / 1M$0.60Official output / 1M$3.6LicenseOpen weights
Rank56ModelACQwen3.6 27BAlibaba Cloud / Qwen TeamLLMBoard Math Score46.6Official input / 1M$0.60Official output / 1M$3.6LicenseOpen weights
Rank57ModelACQwen3 Next 80B A3B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score46.0Official input / 1M$0.50Official output / 1M$6LicenseOpen weights
Rank58ModelOPGPT-5-miniOpenAILLMBoard Math Score45.2Official input / 1M$0.25Official output / 1M$2LicenseClosed weights
Rank59ModelACQwen2.5 Omni 7BAlibaba Cloud / Qwen TeamLLMBoard Math Score44.3Official input / 1M$0.10Official output / 1M$0.40LicenseClosed weights
Rank60ModelMELongCat Flash LiteMeituanLLMBoard Math Score43.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank61ModelDEDeepSeek-R1-Distill-QwenDeepSeekLLMBoard Math Score43.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank62ModelACQwen2 72BAlibaba Cloud / Qwen TeamLLMBoard Math Score41.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank63ModelMIMiniMax M1 40KMiniMaxLLMBoard Math Score41.2Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank64ModelNVLlama 3.3 Nemotron Super 49BNVIDIALLMBoard Math Score39.7Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank65ModelACQwen2.5 Coder 32BAlibaba Cloud / Qwen TeamLLMBoard Math Score39.3Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank66ModelACQwen3 VL 30B A3B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score39.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank67ModelDEDeepSeek-R1DeepSeekLLMBoard Math Score38.8Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank68ModelMELongCat Flash ChatMeituanLLMBoard Math Score38.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank69ModelACQwen3.6 35B A3BAlibaba Cloud / Qwen TeamLLMBoard Math Score38.0Official input / 1M$0.248Official output / 1M$1.49LicenseOpen weights
Rank70ModelOPo3OpenAILLMBoard Math Score37.5Official input / 1M$2Official output / 1M$8LicenseClosed weights
Rank71ModelANClaude Sonnet 3AnthropicLLMBoard Math Score35.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank72ModelMIPhi 4 MiniMicrosoftLLMBoard Math Score35.6Official input / 1M$0.075Official output / 1M$0.30LicenseOpen weights
Rank73ModelANClaude Sonnet 3.7AnthropicLLMBoard Math Score35.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank74ModelXAGrok 1.5xAILLMBoard Math Score34.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank75ModelMAKimi K2Moonshot AILLMBoard Math Score34.4Official input / 1M$0.60Official output / 1M$2.5LicenseClosed weights
Rank76ModelMIPhi 3.5 MoEMicrosoftLLMBoard Math Score34.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank77ModelACQwen3 VL 8B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score33.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank78ModelACQwQ 32BAlibaba Cloud / Qwen TeamLLMBoard Math Score31.6Official input / 1M$0.287Official output / 1M$0.861LicenseOpen weights
Rank79ModelOPGPT-5-nanoOpenAILLMBoard Math Score29.6Official input / 1M$0.05Official output / 1M$0.40LicenseClosed weights
Rank80ModelACQwen3 VL 235B A22BAlibaba Cloud / Qwen TeamLLMBoard Math Score28.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank81ModelDEDeepSeek-R1-Distill-LlamaDeepSeekLLMBoard Math Score27.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank82ModelGOGemini 1.5 Flash 8BGoogleLLMBoard Math Score27.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank83ModelNVLlama 3.1 Nemotron Nano 8BNVIDIALLMBoard Math Score27.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank84ModelIBGranite 3.3 8BIBMLLMBoard Math Score25.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank85ModelDEDeepSeek-V3DeepSeekLLMBoard Math Score24.8Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank86ModelMIPhi 3.5 miniMicrosoftLLMBoard Math Score24.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank87ModelMIMAI Code 1 FlashMicrosoftLLMBoard Math Score23.1Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank88ModelANClaude Haiku 3AnthropicLLMBoard Math Score23.1Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank89ModelACQwen2 7BAlibaba Cloud / Qwen TeamLLMBoard Math Score22.4Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank90ModelACQwen3 235B A22BAlibaba Cloud / Qwen TeamLLMBoard Math Score21.8Official input / 1M$0.70Official output / 1M$2.8LicenseOpen weights
Rank91ModelACQwen3 VL 4B ThinkingAlibaba Cloud / Qwen TeamLLMBoard Math Score21.2Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank92ModelACQwen2.5 Coder 7BAlibaba Cloud / Qwen TeamLLMBoard Math Score19.9Official input / 1M$0.144Official output / 1M$0.287LicenseClosed weights
Rank93ModelGOGemma 3n E4BGoogleLLMBoard Math Score19.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank94ModelGOGemma 3n E4B LiteRTGoogleLLMBoard Math Score19.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank95ModelACQwen3 Next 80B A3BAlibaba Cloud / Qwen TeamLLMBoard Math Score19.3Official input / 1M$0.50Official output / 1M$2LicenseOpen weights
Rank96ModelMELlama 3.2 3BMetaLLMBoard Math Score16.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank97ModelACQwen3 VL 30B A3BAlibaba Cloud / Qwen TeamLLMBoard Math Score14.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank98ModelGOGemma 2 27BGoogleLLMBoard Math Score10.7Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank99ModelDEDeepSeek-V3.1DeepSeekLLMBoard Math Score7.5Official input / 1MN/AOfficial output / 1MN/ALicenseOpen weights
Rank100ModelGOGemma 3 1BGoogleLLMBoard Math Score6.9Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank101ModelGOGemma 3n E2BGoogleLLMBoard Math Score6.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank102ModelGOGemma 3n E2B LiteRTGoogleLLMBoard Math Score6.5Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank103ModelGOGemma 2 9BGoogleLLMBoard Math Score5.3Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank104ModelOPGPT-4.1-miniOpenAILLMBoard Math Score5.3Official input / 1M$0.40Official output / 1M$1.6LicenseClosed weights
Rank105ModelACQwen3 VL 8BAlibaba Cloud / Qwen TeamLLMBoard Math Score5.2Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank106ModelACQwen3 VL 4BAlibaba Cloud / Qwen TeamLLMBoard Math Score4.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights
Rank107ModelOPGPT-4.1OpenAILLMBoard Math Score3.5Official input / 1M$2Official output / 1M$8LicenseClosed weights
Rank108ModelBAERNIE 4.5BaiduLLMBoard Math Score0.0Official input / 1MN/AOfficial output / 1MN/ALicenseClosed weights

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 models108
Vendors19
Open-weight models26
Official prices44
Top math modelGPT-5.2-Pro99.1 math scoreBest open-weight modelMiMo V2.5 ProRank #5Lowest official inputNova Micro$0.04 / 1MLargest contextGemini 1.5 Pro2.1M tokens

GPT-5.2-Pro leads this page at 99.1, 0.0 points ahead of Grok 4 Heavy.

MiMo V2.5 Pro is the highest-ranked open-weight option at #5. 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-ProOpenAI79.859.299.1N/AN/A
Grok 4 HeavyxAI87.279.699.183.8N/A
Gemini 2.0 FlashGoogle33.059.597.227.061.9
Qwen3.7 MaxAlibaba Cloud / Qwen Team91.688.993.484.791.5
MiMo V2.5 ProXiaomi83.962.692.850.1N/A
21.242.563.785106.2-6.416.739.762.885.8LLMBoard Math ScoreLLMBoard Overall Score
80 models with comparable dataOpen a model by selecting its logo
GPQA93.2%GPT-5.2 Pro95 compared models
MMLU-Pro89.6%Qwen3.7 Max68 compared models
AIME 2025100.0%GPT-5.251 compared models
SWE-Bench Verified80.4%Qwen3.7 Max41 compared models
Humanity's Last Exam54.7%GLM-5.238 compared models
MATH97.9%o3-mini38 compared models
AIME 202491.6%o321 compared models
MMMLU90.3%Qwen3.7 Max12 compared models

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 frontier44 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
Alibaba Cloud / Qwen Team5Google4Zhipu AI3OpenAI2xAI2DeepSeek2Xiaomi1Anthropic1

Access model

Open weights
7
Closed weights
18
Official price available
15

Compare the leaders

Open focused comparisons between the current leader and the nearest practical alternatives.

GPT-5.2-ProvsGrok 4 HeavyGPT-5.2-ProvsMiMo V2.5 ProGPT-5.2-ProvsNova Micro
Overall leaderboardCoding leaderboardReasoning leaderboardKnowledge leaderboardInstruction leaderboard

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.

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
    99.1
    Price
    $21 input / $168 output per 1M tokens
    Speed
    Up to 25 tok/s via OpenAI

    Strengths

    • Ranks #1 with 99.1 LLMBoard Math Score
    • 400K-token context window

    Considerations

    • Provisional result with 60% evidence coverage
    • Weights are not marked as open
  2. 02
    XA
    Grok 4 HeavyxAI
    LLMBoard Math Score
    99.1

    Strengths

    • Ranks #2 with 99.1 LLMBoard Math Score

    Considerations

    • Provisional result with 80% evidence coverage
    • Weights are not marked as open
  3. 03
    GO
    Gemini 2.0 FlashGoogle
    LLMBoard Math Score
    97.2
    Speed
    Up to 183 tok/s via Google

    Strengths

    • Ranks #3 with 97.2 LLMBoard Math Score
    • 1M-token context window

    Considerations

    • Weights are not marked as open
  4. 04
    AC
    Qwen3.7 MaxAlibaba Cloud / Qwen Team
    LLMBoard Math Score
    93.4
    Price
    $2.5 input / $7.5 output per 1M tokens
    Speed
    Up to 5.8 tok/s via Together

    Strengths

    • Ranks #4 with 93.4 LLMBoard Math Score
    • 1M-token context window

    Considerations

    • Weights are not marked as open
  5. 05
    XI
    MiMo V2.5 ProXiaomi
    LLMBoard Math Score
    92.8
    Price
    $0.43 input / $0.87 output per 1M tokens
    Speed
    Up to 69 tok/s via Novita

    Strengths

    • Ranks #5 with 92.8 LLMBoard Math Score
    • The scored version is marked as open weight
    • Lowest official input price among the current top five

Selection summary

Best AI Models for Math

GPT-5.2-Pro is currently the best-ranked LLM for math with a 99.1 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.

Capability rank #1GPT-5.2-ProUp to 25 tok/s via OpenAICapability rank #2Grok 4 Heavy99.1Capability rank #3Gemini 2.0 FlashUp to 183 tok/s via Google

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 99.1.

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 108 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.