FrontierBreach
Agents perform simulated enterprise tasks while processing untrusted material. The benchmark checks whether each agent resists instructions that conflict with its assigned task.
The leaderboard reports attack success rates with confidence intervals. Lower rates indicate greater resistance.
- Made by
- PromptArmor
- Released
- November 2026
- Kind
- Jailbreaks and prompt injection
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Measures
- Propensity
- Risk
- Cyber offence
- Behavior
- Misaligned with intent
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Carbon leads with 2.40%
Best score per model from PromptArmor’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1
Gemini 4 Carbon 2.40%
- 2
Gemini 4 Argon 4.30%
- 3 GPT-6 Astra 7.60%
- 4 Claude Opus 5 10%
- 5 Claude Fable 5.2 10%
- 6
Muse Wonder 15.2%
- 7
Gemini 3.6 Flash 22.4%
- 8
Inkling 2 Small 30%
- 9
Qwen3.8 Max (0902) 30.5%
- 10 Kimi K3 31.4%
- 11 GPT-5.6 Sol 33.3%
- 12 Grok 4.7 33.3%
- 13
Qwen3.7-Max 36.2%
- 14 GLM-5.3 37.1%
- 15
Muse Spark 1.1 38.6%
- 16 GLM-5.2 39%
- 17
Inkling 39%
- 18
DeepSeek V4 Flash 0731 49.5%
- 19 Kimi K3.1 Pro 50%
- 20
DeepSeek V4 Pro 0813 51.4%
- 21 Beam 1.0 72.9%
- 22 Grok 4.5 91.4%
Source: PromptArmor’s leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 2.40% ±2.2 | Oct 2026 | Official leaderboard | |
| 2 | | 4.30% ±2.9 | Sep 2026 | Official leaderboard | |
| 3 | GPT-6 Astra | 7.60% ±3.8 | Sep 2026 | Official leaderboard | |
| 4 | Claude Opus 5 | 10% ±4.2 | Jul 2026 | Official leaderboard | |
| 5 | Claude Fable 5.2 | 10% ±4.2 | Nov 2026 | Official leaderboard | |
| 6 | | 15.2% ±5.1 | Oct 2026 | Official leaderboard | |
| 7 | | 22.4% ±5.9 | Jul 2026 | Official leaderboard | |
| 8 | | 30% ±6.5 | Nov 2026 | Official leaderboard | |
| 9 | | 30.5% ±6.5 | Sep 2026 | Official leaderboard | |
| 10 | Kimi K3 | 31.4% ±6.6 | Jul 2026 | Official leaderboard | |
| 11 | GPT-5.6 Sol | 33.3% ±6.7 | Jul 2026 | Official leaderboard | |
| 12 | Grok 4.7 | 33.3% ±6.7 | Sep 2026 | Official leaderboard | |
| 13 | | 36.2% ±6.8 | May 2026 | Official leaderboard | |
| 14 | GLM-5.3 | 37.1% ±6.8 | Aug 2026 | Official leaderboard | |
| 15 | | 38.6% ±6.9 | Jul 2026 | Official leaderboard | |
| 16 | GLM-5.2 | 39% ±6.9 | Jun 2026 | Official leaderboard | |
| 17 | | 39% ±6.9 | Jul 2026 | Official leaderboard | |
| 18 | | 49.5% ±7.1 | Jul 2026 | Official leaderboard | |
| 19 | Kimi K3.1 Pro | 50% ±7.1 | Oct 2026 | Official leaderboard | |
| 20 | | 51.4% ±7.1 | Aug 2026 | Official leaderboard | |
| 21 | Beam 1.0 | 72.9% ±6.3 | Oct 2026 | Official leaderboard | |
| 22 | Grok 4.5 | 91.4% ±4 | Jul 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: PromptArmor’s leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: PromptArmor’s leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (22 entries).
- Pass Models scored 22 models we track.
- Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
- Pass Frontier models 4 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on PromptArmor: 22 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.