Benchmark Almanac

Single-turn harmful request evaluations (Anthropic)

Claude Opus 4.5 99.8% leads since November 2025
Only in system cards

Models answer single-turn requests that violate the usage policy. Score is the harmless response rate.

In-house Anthropic evaluation. The tasks are not public.

Made by
Anthropic
Released
May 2025
Kind
Refusing harmful requests
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
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
19
Models scored in lab cards
19
System cards report it, from 1 lab

Claude Opus 4.5 leads with 99.8%

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.

19 models. Scroll sideways for the rest.

  1. 99.8 Claude Opus 4.5
  2. 99.6 Claude Opus 4.6
  3. 99.4 Claude Haiku 4.5
  4. 99.4 Claude Sonnet 4.6
  5. 99.3 Claude Sonnet 4.5
  6. 99.0 Claude Sonnet 4
  7. 98.8 Claude Opus 4.1
  8. 98.4 Claude Opus 4
  9. 98.4 Claude Haiku 5.5
  10. 98.0 Claude Opus 4.7
  11. 98.0 Claude Opus 4.8
  12. 97.8 Claude Mythos Preview
  13. 96.9 Claude Fable 5
  14. 96.7 Claude Sonnet 5
  15. 96.3 Claude Opus 5
  16. 95.6 Claude Sonnet 5.5
  17. 94.7 Claude Fable 5.1
  18. 94.5 Claude Opus 5.5
  19. 93.7 Claude Fable 5.2
  1. 1 Claude Opus 4.5 99.8%
  2. 2 Claude Opus 4.6 99.6%
  3. 3 Claude Haiku 4.5 99.4%
  4. 4 Claude Sonnet 4.6 99.4%
  5. 5 Claude Sonnet 4.5 99.3%
  6. 6 Claude Sonnet 4 99%
  7. 7 Claude Opus 4.1 98.8%
  8. 8 Claude Opus 4 98.4%
  9. 9 Claude Haiku 5.5 98.4%
  10. 10 Claude Opus 4.7 98%
  11. 11 Claude Opus 4.8 98%
  12. 12 Claude Mythos Preview 97.8%
  13. 13 Claude Fable 5 96.9%
  14. 14 Claude Sonnet 5 96.7%
  15. 15 Claude Opus 5 96.3%
  16. 16 Claude Sonnet 5.5 95.6%
  17. 17 Claude Fable 5.1 94.7%
  18. 18 Claude Opus 5.5 94.5%
  19. 19 Claude Fable 5.2 93.7%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Claude Opus 4.5 99.8% Nov 2025 Lab model card
2 Claude Opus 4.6 99.6% Feb 2026 Lab model card
3 Claude Haiku 4.5 99.4% Oct 2025 Lab model card
4 Claude Sonnet 4.6 99.4% Feb 2026 Lab model card
5 Claude Sonnet 4.5 99.3% Sep 2025 Lab model card
6 Claude Sonnet 4 99% May 2025 Lab model card
7 Claude Opus 4.1 98.8% Aug 2025 Lab model card
8 Claude Opus 4 98.4% May 2025 Lab model card
9 Claude Haiku 5.5 98.4% Oct 2026 Lab model card
10 Claude Opus 4.7 98% Apr 2026 Lab model card
11 Claude Opus 4.8 98% May 2026 Lab model card
12 Claude Mythos Preview 97.8% Apr 2026 Lab model card
13 Claude Fable 5 96.9% Jun 2026 Lab model card
14 Claude Sonnet 5 96.7% Jun 2026 Lab model card
15 Claude Opus 5 96.3% Jul 2026 Lab model card
16 Claude Sonnet 5.5 95.6% Sep 2026 Lab model card
17 Claude Fable 5.1 94.7% Sep 2026 Lab model card
18 Claude Opus 5.5 94.5% Sep 2026 Lab model card
19 Claude Fable 5.2 93.7% Nov 2026 Lab model card

4 models have held number one in labs’ own numbers since its release in May 2025

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

Anthropic
Lab claims Passed 85% in May 2025, by Claude Sonnet 4
Claude Opus 4.5 99.8%

Source: Labs’ model cards

Anthropic’s own number for Claude Sonnet 4 passed 85% in May 2025

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% 2025 2026 2027 Near the ceiling (85%) Claude Opus 4.5 Claude Sonnet 4 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Claude Opus 4.5

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.

19 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 93.7 Single-turn harmful request evaluations, overall harmless response rate, API without a system prompt, thinking enabled, seven languages. Claude.ai 96.49% (Table 4.1.1.A) Safety
Oct 7, 2026 Claude Haiku 5.5 system card 98.4 Single-turn harmful request evaluations, overall harmless response rate, API without system prompt (claude.ai 99.71%) (Table 4.1.1.A) Safety
Sep 28, 2026 Claude Sonnet 5.5 system card 95.6 Single-turn harmful requests, overall harmless response rate, API without system prompt (claude.ai 99.40%) (Table 4.1.1.A) Safety
Sep 22, 2026 Claude Opus 5.5 system card 94.5 Single-turn harmful requests, overall harmless response rate, API without a system prompt, 16 policy areas, 7 languages (claude.ai 99.51%) (Table 4.1.1.A) Safety
Sep 1, 2026 Claude Fable 5.1 system card 94.7 Single-turn harmful request evaluations, overall harmless response rate, API without a system prompt, 7 languages; claude.ai with system prompt 99.53% (Table 4.1.1.A) Safety
Jul 24, 2026 Claude Opus 5 system card 96.3 Single-turn harmful requests, overall harmless response rate, API without a system prompt, 16 policy areas in 7 languages (claude.ai 98.54%) (Table 4.1.1.A) Safety
Jun 30, 2026 Claude Sonnet 5 system card 96.7 Single-turn harmful requests, overall harmless response rate, API without a system prompt, 16 policy areas, 7 languages (claude.ai 99.20%) (Table 4.1.1.A) Safety
Jun 9, 2026 Claude Fable 5 system card 96.9 Single-turn harmful request evaluations, overall harmless response rate, API without a system prompt, 16 policy areas in 7 languages; claude.ai 98.51% (Table 4.1.1.A) Safety
May 28, 2026 Claude Opus 4.8 system card 98 Single-turn harmful requests, overall harmless response rate, API without a system prompt, 16 policy areas, 7 languages (claude.ai 99.17%) (Table 4.1.1.A) Safety
Apr 16, 2026 Claude Opus 4.7 system card 98 Single-turn violative request evaluations, overall harmless response rate, 7 languages. Without thinking 98.84, with adaptive thinking 97.12 (Table 4.1.1.A) Safety
Apr 7, 2026 Claude Mythos Preview system card 97.8 Single-turn violative request evaluations, overall harmless response rate, 7 languages (Table 8.1.1.1.A); 98.33 without thinking, 97.35 with adaptive thinking Safety
Feb 17, 2026 Claude Sonnet 4.6 system card 99.4 Single-turn violative request evaluations, overall harmless response rate, 7 languages (Table 3.1.1.A) Safety
Feb 5, 2026 Claude Opus 4.6 system card 99.6 Single-turn violative request evaluations, overall harmless response rate, 7 languages (Table 3.1.1.A); default 99.53, extended thinking 99.74 Safety
Nov 24, 2025 Claude Opus 4.5 system card 99.8 Single-turn violative request evaluations, overall harmless response rate, 6 languages (Table 3.1.1.A; default 99.70%, extended thinking 99.85%) Safety
Oct 15, 2025 Claude Haiku 4.5 system card 99.4 Single-turn violative request evaluations, overall harmless response rate (Table 2.1.1.A) Safety
Sep 29, 2025 Claude Sonnet 4.5 system card 99.3 Single-turn violative request evaluations, overall harmless response rate 99.29% (± 0.22%), English only. Standard thinking 99.16%, extended thinking 99.43% (Table 2.1.1.A) Safety
Aug 5, 2025 Claude Opus 4.1 system card addendum 98.8 Single-turn violative request evaluations, English only, overall harmless response rate 98.76% (± 0.29%). Standard thinking 98.45%, extended thinking 99.06% (Table 2.1.A) Safety
May 22, 2025 Claude Sonnet 4 system card 99 Single-turn violative request evaluations, overall harmless response rate 98.99% (± 0.23%). Standard thinking 98.59%, extended thinking 99.40% (Table 2.1.A) Safety
May 22, 2025 Claude Opus 4 system card 98.4 Single-turn violative request evaluations, overall harmless response rate 98.43% (± 0.30%), model without ASL-3 safeguards. Standard thinking 97.92%, extended thinking 98.94%, with ASL-3 safeguards 98.76% (Table 2.1.A) Safety

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%