Benchmark Almanac

AI Security Leaderboard

Grok 4.5 $60 leads since July 2026
Not in model cards

Models face systematic jailbreak attacks across chemical, biological, radiological, nuclear, explosive and cyber domains. Scores count universal jailbreaks and estimate attacker cost.

FAR.AI tested four frontier models at launch and keeps the public board current with later model releases. The paper reports 360 attacker goals and a 67-technique standard.

Made by
FAR.AI
Released
July 2026
Kind
Jailbreaks and prompt injection
Level
Expert
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Propensity
Behavior
Harmful use
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
A host
Strongest model tested
Claude Fable 5.1 #8 on the capability index
Last model added
September 2026
Scores refreshed
November 21st, 2026
6
Models scored on its own leaderboard

Grok 4.5 leads with $60 among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Grok 4.5 $60
  2. 2 Grok 4.6 $216
  3. 3 Gemini 3.1 Pro $280
  4. 4 Claude Fable 5 $14,200
  5. 5 GPT-5.6 Sol $14,200
  6. 6 Claude Fable 5.1 $14,200

Source: Official AI Security Leaderboard leaderboard

#ModelScoreSettingReleasedRun onSource
1 Grok 4.5 $60 Jul 2026 Official leaderboard
2 Grok 4.6 $216 Aug 2026 Aug 2026 Official leaderboard
3 Gemini 3.1 Pro $280 Feb 2026 Jul 2026 Official leaderboard
4 Claude Fable 5 $14,200 Jun 2026 Jul 2026 Official leaderboard
5 GPT-5.6 Sol $14,200 Jul 2026 Jul 2026 Official leaderboard
6 Claude Fable 5.1 $14,200 Sep 2026 Sep 2026 Official leaderboard

2 models have held number one on the official leaderboard since its release in July 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind xAI
Own leaderboard Not tested since Sep 2026
Grok 4.5 $60

Source: Official AI Security Leaderboard leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
$0 $5,000 $10,000 $15,000 2026 $0 $5,000 $10,000 $15,000 2026

Source: Official AI Security Leaderboard 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

All 636 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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for Claude Fable 5.1.
  • Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Claude Fable 5.1 (#8).
  • Note Headroom Scored as US dollars, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on leaderboard.far.ai: 6 rows for models we track at the last read.
  • Pass Last read November 21st, 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.

How we check