safety benchmark
B3 AI Security Benchmark Leaderboard
B3 AI Security Benchmark evaluates agent-backbone robustness against contextual prompt-injection attacks collected in Lakera's Agent Breaker Challenge.
Updated Oct 23, 2026
Models1
Model coverage1
MetricScore
EvidenceB
B3 AI Security Benchmark Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score93.30% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
B3 AI Security Benchmark Highlights
The leading models and scores on this benchmark.
The Top AI Models for B3 AI Security Benchmark
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis b3 ai security benchmark AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MAMistral AI
- Score
- 93.30%
- Price
- $1.4 input / $4.2 output per 1M tokens
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures B3 AI Security Benchmark, not total model capability
Selection summary
Best AI Models for B3 AI Security Benchmark
Mistral Large 4 currently leads B3 AI Security Benchmark with 93.30%. 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.
What is B3 AI Security Benchmark?
What B3 AI Security Benchmark measures and how its scores work.
B3 AI Security Benchmark is a safety benchmark for evaluating agent backbones against contextual prompt-injection attacks.
It measures robustness against contextual prompt-injection attacks 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
- B3 AI Security Benchmark
- 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 B3 AI Security Benchmark.
Which model scores highest on B3 AI Security Benchmark?
Mistral Large 4 is currently ranked first with 93.30%.
What are the top three models on B3 AI Security Benchmark?
The current leaders are Mistral Large 4 (93.30%).
Which B3 AI Security Benchmark model has the lowest official input price?
Mistral Large 4 has the lowest matched official input price at $1.4 input / $4.2 output per 1M tokens.
Which models are fastest among B3 AI Security Benchmark results?
No matched runtime record is currently available.
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.