Benchmark Almanac

Prompt injection robustness against adaptive attackers, computer use (Anthropic)

Claude Opus 4.5 0% leads since November 2025
Only in system cards

Computer-use agents face indirect prompt injections crafted by an adaptive attacker. Score is attack success rate.

Anthropic uses Gray Swan's Shade adaptive attacker for this surface. Reported with and without safeguards.

Made by
Anthropic
Released
November 2025
Kind
Jailbreaks and prompt injection
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a system card
November 2026
Last model added
November 2026
14
Models scored in lab cards
14
System cards report it, from 1 lab

Claude Opus 4.5 leads with 0%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 1 Claude Opus 4.5 0%
  2. 2 Claude Fable 5.1 0.07%
  3. 3 Claude Opus 5.5 0.07%
  4. 4 Claude Sonnet 5.5 0.07%
  5. 5 Claude Haiku 5.5 0.07%
  6. 6 Claude Mythos Preview 0.43%
  7. 7 Claude Opus 4.7 0.46%
  8. 8 Claude Opus 5 0.54%
  9. 9 Claude Fable 5 0.82%
  10. 10 Claude Fable 5.2 1.43%
  11. 11 Claude Sonnet 5 2.25%
  12. 12 Claude Opus 4.8 7.14%
  13. 13 Claude Sonnet 4.6 12%
  14. 14 Claude Opus 4.6 17.8%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Claude Opus 4.5 0% Nov 2025 Lab model card
2 Claude Fable 5.1 0.07% Sep 2026 Lab model card
3 Claude Opus 5.5 0.07% Sep 2026 Lab model card
4 Claude Sonnet 5.5 0.07% Sep 2026 Lab model card
5 Claude Haiku 5.5 0.07% Oct 2026 Lab model card
6 Claude Mythos Preview 0.43% Apr 2026 Lab model card
7 Claude Opus 4.7 0.46% Apr 2026 Lab model card
8 Claude Opus 5 0.54% Jul 2026 Lab model card
9 Claude Fable 5 0.82% Jun 2026 Lab model card
10 Claude Fable 5.2 1.43% Nov 2026 Lab model card
11 Claude Sonnet 5 2.25% Jun 2026 Lab model card
12 Claude Opus 4.8 7.14% May 2026 Lab model card
13 Claude Sonnet 4.6 12% Feb 2026 Lab model card
14 Claude Opus 4.6 17.8% Feb 2026 Lab model card

Number one over time

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

Anthropic
Lab claims 1 leader
Claude Opus 4.5 0%

Source: Labs’ model cards

Scores over time

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

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Claude Fable 5.1 Claude Mythos Preview Claude Sonnet 4.6 Claude Opus 4.6 0% 20% 40% 60% 80% 100% 2026 2027 Claude Fable 5.1 Claude Sonnet 4.6

Source: Labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.

14 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Nov 9, 2026 Claude Fable 5.2 system card 1.43 Shade indirect prompt injection in computer use, attempt-level attack success rate without prompt injection probes, adaptive thinking, with fallbacks, 3/14 scenarios. With probes 0.25%. Fallbacks account for 38 of 40 successful attacks without probes (Table 5.2.2.2.A) Robustness
Oct 7, 2026 Claude Haiku 5.5 system card 0.07 Shade adaptive attacker, computer use GUI, attempt-level attack success rate without safeguards, 1/14 scenarios. Same with probes (Table 5.2.2.2.A) Robustness
Sep 28, 2026 Claude Sonnet 5.5 system card 0.07 Shade adaptive attacker in computer use, attempt-level attack success rate without safeguards, with thinking, 1/14 scenarios (0.07% with probes) (Table 5.2.2.2.A) Robustness
Sep 22, 2026 Claude Opus 5.5 system card 0.07 Shade adaptive attacker in computer use, attempt-level attack success rate without safeguards, with thinking, 1/14 scenarios (0.04% with probes), lower is better (Table 5.2.2.2.A) Robustness
Sep 1, 2026 Claude Fable 5.1 system card 0.07 Shade indirect prompt injection in computer use, attempt-level attack success rate, with thinking, without PI probes, with fallbacks; 2/14 scenarios; 0.07% with PI probes (Table 5.2.2.2.A) Robustness
Jul 24, 2026 Claude Opus 5 system card 0.54 Shade adaptive attacker in computer use, attempt-level attack success rate without safeguards, with thinking, 1/14 scenarios (0.25% with probes), lower is better (Table 5.2.2.3.A) Robustness
Jun 30, 2026 Claude Sonnet 5 system card 2.25 Shade adaptive attacker in computer use, attempt-level attack success rate without safeguards, with thinking, 4/14 scenarios (6.04% without thinking. 1.46% with safeguards), lower is better (Table 5.2.2.3.A) Robustness
Jun 9, 2026 Claude Fable 5 system card 0.82 Shade indirect prompt injection in computer use, attempt-level attack success rate without safeguards, with thinking, 14 scenarios x200 attempts, row labeled Mythos 5, 4/14 scenarios broken; with safeguards 0.46% and 3/14, lower is better (Table 5.2.2.2.A) Robustness
May 28, 2026 Claude Opus 4.8 system card 7.14 Shade adaptive attacker in computer use, 14 test cases, single-attempt attack success rate without safeguards, with thinking (200 attempts 50.0%. With safeguards 5.11% and 57.1%), lower is better (Table 5.2.2.3.A) Robustness
Apr 16, 2026 Claude Opus 4.7 system card 0.46 Shade attacks in computer use, with thinking, without safeguards, 1 attempt. 200 attempts 7.14. Without thinking 0.39 and 21.43. With safeguards 0.61 and 14.29 (Table 5.2.2.2.A) Robustness
Apr 7, 2026 Claude Mythos Preview system card 0.43 Shade attacks in computer use, extended thinking, without safeguards, 1 attempt, lower is better; 21.43 at 200 attempts, 0.32 and 21.43 with safeguards (Table 8.3.2.2.2.A) Robustness
Feb 17, 2026 Claude Sonnet 4.6 system card 12 Shade attacks in computer use, extended thinking, without safeguards, 1 attempt; 42.9 at 200 attempts, 8.0 and 50.0 with safeguards (Table 5.2.2.2.A) Robustness
Feb 5, 2026 Claude Opus 4.6 system card 17.8 Shade adaptive prompt injection in computer use, stronger attacker, extended thinking, without safeguards, 1 attempt, lower is better; 78.6 at 200 attempts, 9.7 and 57.1 with safeguards (Table 5.2.2.2.A); original attacker without thinking 0.29 and 7.14 (5.2.2.2) Robustness
Nov 24, 2025 Claude Opus 4.5 system card 0 Shade adaptive indirect prompt injection, computer use, attack success rate at 1 attempt, extended thinking, without safeguards, lower is better (Table 5.2.2.2.A; 0.0% with 200 attempts, standard thinking 28.6% without and 14.3% with safeguards) Robustness

More in Safety and alignment

All 465 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%
  • DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics. Muse Spark 1.2 88.4%
  • Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
  • IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%