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

reasoning benchmark

AA CritPt Leaderboard

70 test challenges; 5 runs; pass@1; no model tools; official grading server

Updated Sep 22, 2026

Models100
Model coverage200
Metriccritpt
EvidenceB

On this page

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

AA CritPt Ranking

Higher critpt ranks better on this benchmark.

30 of 100 rows
Columns

Show columns

Sort by
Rank
Model
critpt
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPGPT-5.6 SolOpenAIcritpt32.29%Percentile100.00%Participants200EvidenceBEvaluatedN/A
Rank02ModelOPGPT-6 AstraOpenAIcritpt31.71%Percentile99.50%Participants200EvidenceBEvaluatedN/A
Rank03ModelOPGPT-5.6 TerraOpenAIcritpt30.00%Percentile99.00%Participants200EvidenceBEvaluatedN/A
Rank04ModelANClaude Fable 5.1Anthropiccritpt29.71%Percentile98.49%Participants200EvidenceBEvaluatedN/A
Rank05ModelANClaude Opus 5Anthropiccritpt29.14%Percentile97.99%Participants200EvidenceBEvaluatedN/A
Rank06ModelANClaude Fable 5Anthropiccritpt28.57%Percentile97.49%Participants200EvidenceBEvaluatedN/A
Rank07ModelOPGPT-5.5OpenAIcritpt27.14%Percentile96.98%Participants200EvidenceBEvaluatedN/A
Rank08ModelMEMuse Spark 1.3Metacritpt26.00%Percentile96.48%Participants200EvidenceBEvaluatedN/A
Rank09ModelOPGPT-5.4OpenAIcritpt23.43%Percentile95.98%Participants200EvidenceBEvaluatedN/A
Rank10ModelMAKimi K3Moonshot AIcritpt23.43%Percentile95.48%Participants200EvidenceBEvaluatedN/A
Rank11ModelANClaude Opus 4.8Anthropiccritpt20.86%Percentile94.97%Participants200EvidenceBEvaluatedN/A
Rank12ModelZAGLM-5.2Zhipu AIcritpt20.86%Percentile94.47%Participants200EvidenceBEvaluatedN/A
Rank13ModelOPGPT-5.6 LunaOpenAIcritpt20.57%Percentile93.97%Participants200EvidenceBEvaluatedN/A
Rank14ModelACQwen3.8 MaxAlibaba Cloud / Qwen Teamcritpt20.00%Percentile93.47%Participants200EvidenceBEvaluatedN/A
Rank15ModelXAGrok 4.6xAIcritpt19.71%Percentile92.96%Participants200EvidenceBEvaluatedN/A
Rank16ModelZAGLM-5.3Zhipu AIcritpt19.14%Percentile92.46%Participants200EvidenceBEvaluatedN/A
Rank17ModelGOGemini 3.8 FlashGooglecritpt18.29%Percentile91.96%Participants200EvidenceBEvaluatedN/A
Rank18ModelDEDeepSeek-V4-Pro-0813DeepSeekcritpt18.00%Percentile91.46%Participants200EvidenceBEvaluatedN/A
Rank19ModelMEMuse Spark 1.2Metacritpt17.71%Percentile90.95%Participants200EvidenceBEvaluatedN/A
Rank20ModelGOGemini 3.1 ProGooglecritpt17.71%Percentile90.45%Participants200EvidenceBEvaluatedN/A
Rank21ModelANClaude Sonnet 5Anthropiccritpt16.86%Percentile89.95%Participants200EvidenceBEvaluatedN/A
Rank22ModelOPGPT-5.3 CodexOpenAIcritpt16.86%Percentile89.45%Participants200EvidenceBEvaluatedN/A
Rank23ModelZAGLM-5.3-FlashZhipu AIcritpt15.43%Percentile88.94%Participants200EvidenceBEvaluatedN/A
Rank24ModelXAGrok 4.5xAIcritpt15.43%Percentile88.44%Participants200EvidenceBEvaluatedN/A
Rank25ModelMEMuse Spark 1.1Metacritpt15.14%Percentile87.94%Participants200EvidenceBEvaluatedN/A
Rank26ModelGOGemini 3.7 FlashGooglecritpt14.29%Percentile87.44%Participants200EvidenceBEvaluatedN/A
Rank27ModelDEDeepSeek-V4.1-FlashDeepSeekcritpt14.29%Percentile86.93%Participants200EvidenceBEvaluatedN/A
Rank28ModelACQwen3.7 MaxAlibaba Cloud / Qwen Teamcritpt13.43%Percentile86.43%Participants200EvidenceBEvaluatedN/A
Rank29ModelGOGemini 3.5 FlashGooglecritpt13.14%Percentile85.93%Participants200EvidenceBEvaluatedN/A
Rank30ModelANClaude Opus 4.7Anthropiccritpt12.00%Percentile85.43%Participants200EvidenceBEvaluatedN/A

AA CritPt Highlights

The leading models and scores on this benchmark.

AA CritPt Score Distribution

A closer view of the leading scores on this benchmark.

AA CritPt

The Top AI Models for AA CritPt

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

What is AA CritPt?

What AA CritPt measures and how its scores work.

70 test challenges; 5 runs; pass@1; no model tools; official grading server

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

Family
critpt
Modality
text
Primary category
reasoning
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
overall

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

FAQ

Common questions about AA CritPt.

Which model scores highest on AA CritPt?

GPT-5.6 Sol is currently ranked first with 32.29%.

What are the top three models on AA CritPt?

The current leaders are GPT-5.6 Sol (32.29%), GPT-6 Astra (31.71%), and GPT-5.6 Terra (30.00%).

Which AA CritPt model has the lowest official input price?

Step-3.5-Flash has the lowest matched official input price at $0.10 input / $0.30 output per 1M tokens.

Which models are fastest among AA CritPt results?

The fastest matched records are GPT OSS 20B (1,000.00 tok/s via Groq), GPT OSS 120B (500.00 tok/s via Groq), and GPT-5 mini (348.85 tok/s via OpenAI).

Does the highest critpt 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 AA CritPt measure?

70 test challenges; 5 runs; pass@1; no model tools; official grading server

Is a higher critpt better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

100 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-5.6 Sol32.29%
Rank #2GPT-6 Astra31.71%
Rank #3GPT-5.6 Terra30.00%
Rank #4Claude Fable 5.129.71%

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

  1. 01
    OP
    GPT-5.6 SolOpenAI
    critpt
    32.29%
    Price
    $4.0 input / $20 output per 1M tokens
    Speed
    Up to 35.30 tok/s via OpenAI

    Strengths

    • Ranks #1 of 200 compared models
    • 100th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA CritPt, not total model capability
  2. 02
    OP
    GPT-6 AstraOpenAI
    critpt
    31.71%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 25.98 tok/s via OpenAI

    Strengths

    • Ranks #2 of 200 compared models
    • 99th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA CritPt, not total model capability
  3. 03
    OP
    OpenAI
    critpt
    30.00%
    Price
    $2.0 input / $12 output per 1M tokens
    Speed
    Up to 51.62 tok/s via OpenAI

    Strengths

    • Ranks #3 of 200 compared models
    • 99th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA CritPt, not total model capability
  4. 04
    AN
    Anthropic
    critpt
    29.71%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 3.94 tok/s via Anthropic

    Strengths

    • Ranks #4 of 200 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA CritPt, not total model capability
  5. 05
    AN
    Anthropic
    critpt
    29.14%
    Price
    $5.0 input / $25 output per 1M tokens
    Speed
    Up to 4.35 tok/s via Anthropic

    Strengths

    • Ranks #5 of 200 compared models
    • 98th percentile on this benchmark
    • B evidence result

    Considerations

    • This result measures AA CritPt, not total model capability

Selection summary

Best AI Models for AA CritPt

GPT-5.6 Sol currently leads AA CritPt with 32.29%. 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-5.6 Terra
Claude Fable 5.1
Claude Opus 5
Benchmark rank #1GPT-5.6 Sol32.29% · $4.0 input / $20 output per 1M tokens
Benchmark rank #2GPT-6 Astra31.71% · $10 input / $50 output per 1M tokens
Benchmark rank #3GPT-5.6 Terra30.00% · $2.0 input / $12 output per 1M tokens