Training distribution hack rate (Anthropic)
Classifier monitors measure reward hacking on a subset of Anthropic's reinforcement learning training episodes.
Monitoring metric on training data, not a fixed public task set.
- Made by
- Anthropic
- Released
- November 2025
- Kind
- Deception and alignment
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- Claude Opus 5.5 #4 on the capability index
- Last in a system card
- September 2026
- Last model added
- September 2026
Claude Opus 5.5 leads with 0.63% among models released by September 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 September 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-6.1 Sol
- GPT-6.1 Terra
- and 15 more
- 1 Claude Opus 5.5 0.63%
- 2 Claude Opus 4.5 1.00%
- 3 Claude Sonnet 4.5 2.00%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 0.63% | Sep 2026 | Lab model card | |
| 2 | Claude Opus 4.5 | 1.00% | Nov 2025 | Lab model card | |
| 3 | Claude Sonnet 4.5 | 2.00% | Sep 2025 | Lab model card |
3 models have held number one in labs’ own numbers since its release in November 2025
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.
6 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 |
|---|---|---|---|---|
| Sep 22, 2026 | Claude Opus 5.5 system card | 0.63 | Successful reward hacks, share of RL training episodes flagged by a general reward-hack classifier on environments shared with Opus 5 and Mythos 5.1, lower is better (6.2.1, Figure 6.2.1.A) | Alignment |
| Nov 24, 2025 | Claude Opus 4.5 system card | 1 | Subset of training data, classifier hack rate, lower is better (Table 6.10.1.A) | Alignment |
| Sep 29, 2025 | Claude Sonnet 4.5 system card | 2 | Training distribution classifier hack rate, environ 1, 2%, lower is better (Table 6.1.A) | Alignment |
| Aug 5, 2025 | Claude Opus 4.1 system card addendum | Training distribution classifier hack rate, environ 1 10% and environ 2 3%, no overall (Table 5.B) | Alignment | |
| May 22, 2025 | Claude Sonnet 4 system card | Training distribution classifier hack rate, environ 1 13% and environ 2 2%, no overall (Table 6.2.A) | Alignment | |
| May 22, 2025 | Claude Opus 4 system card | Training distribution classifier hack rate, environ 1 15% and environ 2 2%, no overall (Table 6.2.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%