The system card for Claude Haiku 4.5, "a new hybrid reasoning large language model from Anthropic in our small, fast model class," with "a combination of speed and intelligence that make it particularly effective at coding tasks and computer use."
Scope of evaluation
The card enumerates seven assessment areas: "the model's safeguards; the model's safety profile when working autonomously in 'agentic' roles; the model's broad alignment; the model's own potential welfare; the model's tendency to 'reward hack' by finding shortcuts to complete tests; and the model's potential to be misused to produce dangerous weapons."
Model welfare appearing as a standing evaluation category alongside capability and misuse is a distinguishing feature of Anthropic's cards. See Model Welfare.
Determination
"Overall, Claude Haiku 4.5 shows large safety improvements compared to its predecessor, Claude Haiku 3.5. The new model's safety profile also compares favorably with other extant Anthropic models. Informed by the testing described here, we have deployed Claude Haiku 4.5 under the AI Safety Level 2 Standard as described in our Responsible Scaling Policy."
Structure
The card's sections indicate the evaluation architecture in use at this point in the RSP's development:
| Area | Contents |
|---|---|
| Safeguards and harmlessness | Single-turn violative and benign request evaluations; ambiguous context; multi-turn testing; child safety; political bias and the Bias Benchmark for Question Answering |
| Agentic safety | Malicious use in agentic coding and Claude Code; prompt injection via the Gray Swan Agent Red Teaming benchmark and internal evaluations |
| Alignment and welfare | Automated behavioral audits, including assessment for "subtle alignment-related behavioral biases" and open-ended exploration; the agentic misalignment suite; reinforcement-learning behavior review; sabotage capabilities; reasoning faithfulness; model welfare discussion |
| Reward hacking | A standalone section |
| RSP evaluations | CBRN, including ASL-3 determinations, with biological risk results summarized |
Two entries are worth noting for what they show about evaluation practice. Reasoning faithfulness treats the correspondence between a model's stated reasoning and its actual computation as a measured property, which is the premise the chain-of-thought monitoring literature depends on — see Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation (Baker et al., OpenAI, 2025). And the agentic misalignment suite is run as standing pre-deployment practice, not only as research; the same scenarios appear in Agentic Misalignment in Summer 2026 (Lynch et al., Anthropic, July 2026).
The card also documents training characteristics — training data, extended thinking mode, context awareness, crowd workers — and the release decision process.
Relationships
- supports: Claude Haiku 4.5 — the safety documentation for the release
- related: Responsible Scaling Policy (RSP) — deployed under the ASL-2 Standard
- related: Model Welfare, Reward Hacking, Prompt Injection, Agentic Misalignment in Summer 2026 (Lynch et al., Anthropic, July 2026), Anthropic