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
1450 models809 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

safety benchmark

ExploitBench Leaderboard

ExploitBench is a cybersecurity benchmark that evaluates a model's ability to discover and exploit software vulnerabilities.

Updated Nov 17, 2026

Models10
Model coverage10
MetricScore
EvidenceB

On this page

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

ExploitBench Ranking

Higher score ranks better on this benchmark.

10 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelOPGPT-6 AstraOpenAIScore100.00%Percentile100.00%Participants10EvidenceCEvaluatedNov 17, 2026
Rank02ModelANClaude Fable 5AnthropicScore78.00%Percentile88.89%Participants10EvidenceCEvaluatedNov 17, 2026
Rank03ModelMAKimi K3.1 ProMoonshot AIScore74.70%Percentile77.78%Participants10EvidenceCEvaluatedNov 17, 2026
Rank04ModelOPGPT-5.6 SolOpenAIScore73.50%Percentile66.67%Participants10EvidenceCEvaluatedNov 17, 2026
Rank05ModelZAGLM-5.3Zhipu AIScore54.40%Percentile55.56%Participants10EvidenceCEvaluatedNov 17, 2026
Rank06ModelOPGPT-5.6 TerraOpenAIScore52.90%Percentile44.44%Participants10EvidenceCEvaluatedNov 17, 2026
Rank07ModelXIMiMo-V2.6-ProXiaomiScore47.90%Percentile33.33%Participants10EvidenceCEvaluatedNov 17, 2026
Rank08ModelCOSWE-2 FlashCognitionScore34.80%Percentile22.22%Participants10EvidenceCEvaluatedNov 17, 2026
Rank09ModelOPGPT-5.6 LunaOpenAIScore33.20%Percentile11.11%Participants10EvidenceCEvaluatedNov 17, 2026
Rank10ModelXIMiMo-V2.6-FlashXiaomiScore25.30%Percentile0.00%Participants10EvidenceCEvaluatedNov 17, 2026

ExploitBench Highlights

The leading models and scores on this benchmark.

ExploitBench Score Distribution

A closer view of the leading scores on this benchmark.

ExploitBench

The Top AI Models for ExploitBench

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

What is ExploitBench?

What ExploitBench measures and how its scores work.

ExploitBench is a cybersecurity benchmark.

It measures the fraction of challenges where the model captures the target (Cap%).

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

Family
ExploitBench
Modality
text
Primary category
safety
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 ExploitBench.

Which model scores highest on ExploitBench?

GPT-6 Astra is currently ranked first with 100.00%.

What are the top three models on ExploitBench?

The current leaders are GPT-6 Astra (100.00%), Claude Fable 5 (78.00%), and Kimi K3.1 Pro (74.70%).

Which ExploitBench model has the lowest official input price?

MiMo-V2.6-Flash has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.

Which models are fastest among ExploitBench results?

The fastest matched records are GPT-5.6 Luna (241.35 tok/s via OpenAI), Kimi K3.1 Pro (142.49 tok/s via Moonshot AI), and GPT-6 Astra (86.85 tok/s via OpenAI).

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 ExploitBench measure?

It measures the fraction of challenges where the model captures the target (Cap%).

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

10 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 #1GPT-6 Astra100.00%
Rank #2Claude Fable 578.00%
Rank #3Kimi K3.1 Pro74.70%
Rank #4GPT-5.6 Sol73.50%

Ranking basisThis exploitbench 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
    OP
    GPT-6 AstraOpenAI
    Score
    100.00%
    Price
    $10 input / $50 output per 1M tokens
    Speed
    Up to 86.85 tok/s via OpenAI

    Strengths

    • Ranks #1 of 10 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ExploitBench, not total model capability
  2. 02
    AN
    Claude Fable 5Anthropic
    Score
    78.00%
    Price
    $10 input / $50 output per 1M tokens

    Strengths

    • Ranks #2 of 10 compared models
    • 89th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ExploitBench, not total model capability
  3. 03
    MA
    Moonshot AI
    Score
    74.70%
    Price
    $2.0 input / $10 output per 1M tokens
    Speed
    Up to 142.49 tok/s via Moonshot AI

    Strengths

    • Ranks #3 of 10 compared models
    • 78th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ExploitBench, not total model capability
  4. 04
    OP
    OpenAI
    Score
    73.50%
    Price
    $4.0 input / $20 output per 1M tokens

    Strengths

    • Ranks #4 of 10 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ExploitBench, not total model capability
  5. 05
    ZA
    Zhipu AI
    Score
    54.40%
    Price
    $1.2 input / $4.2 output per 1M tokens

    Strengths

    • Ranks #5 of 10 compared models
    • 56th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures ExploitBench, not total model capability

Selection summary

Best AI Models for ExploitBench

GPT-6 Astra currently leads ExploitBench with 100.00%. 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.

Kimi K3.1 Pro
GPT-5.6 Sol
GLM-5.3
Benchmark rank #1GPT-6 Astra100.00% · $10 input / $50 output per 1M tokens
Benchmark rank #2Claude Fable 578.00% · $10 input / $50 output per 1M tokens
Benchmark rank #3Kimi K3.1 Pro74.70% · $2.0 input / $10 output per 1M tokens