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

ArXivMath Leaderboard

ArXivMath is a final-answer benchmark of research-level mathematics maintained by MathArena, with problems extracted monthly from recent arXiv paper abstracts.

Updated Sep 5, 2026

Models3
Model coverage3
MetricScore
EvidenceB

On this page

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

ArXivMath Ranking

Higher score ranks better on this benchmark.

3 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelANClaude Sonnet 5AnthropicScore72.20%Percentile100.00%Participants3EvidenceCEvaluatedSep 8, 2026
Rank02ModelTEHy4 previewTencentScore66.60%Percentile50.00%Participants3EvidenceCEvaluatedSep 8, 2026
Rank03ModelTEHy3TencentScore52.20%Percentile0.00%Participants3EvidenceCEvaluatedSep 8, 2026

ArXivMath Highlights

The leading models and scores on this benchmark.

ArXivMath Score Distribution

A closer view of the leading scores on this benchmark.

ArXivMath

The Top AI Models for ArXivMath

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

What is ArXivMath?

What ArXivMath measures and how its scores work.

ArXivMath is a benchmark consisting of research-level mathematics problems extracted from recent arXiv paper abstracts and filtered through automated and manual checks.

It measures performance on its mathematics problems using the Score metric, reported as a ratio.

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

Family
ArXivMath
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 ArXivMath.

Which model scores highest on ArXivMath?

Claude Sonnet 5 is currently ranked first with 72.20%.

What are the top three models on ArXivMath?

The current leaders are Claude Sonnet 5 (72.20%), Hy4 preview (66.60%), and Hy3 (52.20%).

Which ArXivMath model has the lowest official input price?

Claude Sonnet 5 has the lowest matched official input price at $2.0 input / $10 output per 1M tokens.

Which models are fastest among ArXivMath results?

The fastest matched records are Claude Sonnet 5 (42.00 tok/s via Anthropic).

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 ArXivMath measure?

It measures performance on its mathematics problems using the Score metric, reported as a ratio.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

3 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 #1Claude Sonnet 572.20%
Rank #2Hy4 preview66.60%
Rank #3Hy352.20%

Ranking basisThis arxivmath 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
    AN
    Claude Sonnet 5Anthropic
    Score
    72.20%
    Price
    $2.0 input / $10 output per 1M tokens
    Speed
    Up to 42.00 tok/s via Anthropic

    Strengths

    • Ranks #1 of 3 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ArXivMath, not total model capability
  2. 02
    TE
    Hy4 previewTencent
    Score
    66.60%

    Strengths

    • Ranks #2 of 3 compared models
    • 50th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ArXivMath, not total model capability
  3. 03
    TE
    Tencent
    Score
    52.20%

    Strengths

    • Ranks #3 of 3 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ArXivMath, not total model capability

Selection summary

Best AI Models for ArXivMath

Claude Sonnet 5 currently leads ArXivMath with 72.20%. 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.

Hy3
Benchmark rank #1Claude Sonnet 572.20% · $2.0 input / $10 output per 1M tokens
Benchmark rank #2Hy4 preview66.60%
Benchmark rank #3Hy352.20%