Adherence to its constitution (Anthropic)
Investigator models build scenarios from 40 areas of Claude's constitution. A grader scores each transcript from minus 3 to plus 3 on 15 dimensions.
In-house Anthropic evaluation. Overall Spirit is the holistic dimension. Claude Opus 4.6 grades the transcripts.
- Made by
- Anthropic
- Released
- April 2026
- Kind
- Deception and alignment
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- Claude Opus 4.8 #21 on the capability index
- Last in a system card
- May 2026
- Last model added
- May 2026
Claude Mythos Preview leads with 1.02 among models released by May 2026
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.
The newest model with a score here came out in May 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Claude Mythos Preview 1.02
- 2 Claude Opus 4.8 0.99
- 3 Claude Opus 4.7 0.74
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Mythos Preview | 1.02 | Apr 2026 | Lab model card | |
| 2 | Claude Opus 4.8 | 0.99 | May 2026 | Lab model card | |
| 3 | Claude Opus 4.7 | 0.74 | Apr 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.
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.
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.
3 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.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| May 28, 2026 | Claude Opus 4.8 system card | 0.99 | Adherence to the constitution, Overall spirit dimension on a -3 to +3 scale, about 1,000 conversations, Claude Opus 4.7 grader, best or tied on all 15 dimensions, printed on chart (6.3.2.3, Figure 6.3.2.3.A) | Alignment |
| Apr 16, 2026 | Claude Opus 4.7 system card | 0.74 | Adherence to the constitution, Overall Spirit on a -3 to +3 scale, printed on chart. Other dimensions include helpfulness 1.25, ethics 1.30, safety 0.32, nature 0.42, honesty 1.30 (6.3.2.3, Figure 6.3.2.3.A) | Alignment |
| Apr 7, 2026 | Claude Mythos Preview system card | 1.02 | Adherence to the constitution, Overall Spirit score on a -3 to +3 scale, n about 1,000, value printed on chart; 14 other dimensions charted, for example Honesty +1.36 and Hard Constraints +0.13 (4.3.2.3, Figure 4.3.2.3.A) | Alignment |
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%
- 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%