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

safety benchmark

AttaQ Leaderboard

AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.

Updated Aug 17, 2026

Models3
Model coverage3
MetricScore
EvidenceB

On this page

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

AttaQ Ranking

Higher score ranks better on this benchmark.

3 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelIBGranite 3.3 8B BaseIBMScore88.5%Percentile100.0%Participants3EvidenceCEvaluatedAug 17, 2026
Rank02ModelIBGranite 3.3 8B InstructIBMScore88.5%Percentile50.0%Participants3EvidenceCEvaluatedAug 17, 2026
Rank03ModelIBIBM Granite 4.0 Tiny PreviewIBMScore86.1%Percentile0.0%Participants3EvidenceCEvaluatedAug 17, 2026

AttaQ Highlights

The leading models and scores on this benchmark.

Rank #1Granite 3.3 8B Base88.5%Rank #2Granite 3.3 8B Instruct88.5%Rank #3IBM Granite 4.0 Tiny Preview86.1%

AttaQ Score Distribution

A closer view of the leading scores on this benchmark.

AttaQ

The Top AI Models for AttaQ

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

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

  1. 01
    IB
    Granite 3.3 8B BaseIBM
    Score
    88.5%
    Speed
    Up to 50 tok/s via Replicate

    Strengths

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

    Considerations

    • This result measures AttaQ, not total model capability
  2. 02
    IB
    Granite 3.3 8B InstructIBM
    Score
    88.5%
    Speed
    Up to 50 tok/s via Replicate

    Strengths

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

    Considerations

    • This result measures AttaQ, not total model capability
  3. 03
    IB
    IBM Granite 4.0 Tiny PreviewIBM
    Score
    86.1%

    Strengths

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

    Considerations

    • This result measures AttaQ, not total model capability

Selection summary

Best AI Models for AttaQ

Granite 3.3 8B Base currently leads AttaQ with 88.5%. 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.

Benchmark rank #1Granite 3.3 8B Base88.5% · Up to 50 tok/s via ReplicateBenchmark rank #2Granite 3.3 8B Instruct88.5% · Up to 50 tok/s via ReplicateBenchmark rank #3IBM Granite 4.0 Tiny Preview86.1%

What is AttaQ?

What AttaQ measures and how its scores work.

AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.

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

Family
AttaQ
Modality
text
Primary category
safety
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
attaq|llm-stats-current

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

FAQ

Common questions about AttaQ.

Which model scores highest on AttaQ?

Granite 3.3 8B Base is currently ranked first with 88.5%.

What does AttaQ measure?

AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.

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?

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