Section 4.5). The models behave accordingly: with thinking enabled and the reasoning span forced, they produce no tool calls; with thinking enabled but not forced, they tend to skip the reasoning span and answer as in non-thinking mode. At launch the serving stacks additionally mis-parse tool calls emitted under thinking, dropping the call terminator. Inference providers therefore expose the two features as mutually exclusive. More generally, the post-training of this release is not designed for agentic use: tool-use behavior comes from supervised finetuning alone, we exclude tool-use prompts from reinforcement learning, and we do not evaluate multi-turn tool use (Table 37 covers the single-turn categories of BFCL). The 8B further remains weak on parallel calls, often producing a single call where several are requested.
7.3 Broader Impact
Apertus 1.5 releases the weights, the data recipe, the training and evaluation code, and the charter its alignment follows, and trains only on publicly available data (Section 3.1). We enumerate every dataset, its license, and its filtering, and we publish the data ablations, so the training data and its processing can be inspected in full. The recipes of Section 3 and Section 4 are the ones we ran, so institutions that cannot train such models from scratch can continue, finetune, or distill them on their own infrastructure. The models can be deployed without dependence on a vendor, which matters for public administrations, regulated sectors, and research that needs a model whose behavior is fixed and documented.
Openness extends to the values to which models are aligned. For most released models, the alignment data and objectives are undisclosed, so users observe a behavior but not the intent behind it. The Apertus charter, introduced with Apertus 1.0 (Hernández-Cano et al., 2026), states the principles the models are aligned to; the charter-alignment stage of Section 4.6.2 trains the released 8B against it with a published recipe and judge prompts (Appendix G); and the charter-alignment score of Section 5.3.2 measures how far each released checkpoint follows it. A deployer who disagrees with a principle can see what to change, and retrain.
Roughly 40% of the pretraining data of Apertus 1.0 is non-English, the post-training data of this release adds multilingual instruction data, and the evaluations of Section 5.4 place the models at their strongest relative position on multilingual and cultural benchmarks, including the national languages of Switzerland and Romansh (Section 4.2.3). For communities whose languages are underrepresented in commercial models, an open model that can be adapted further is a direct benefit, within the coverage limits of Section 7.2.
We keep the data measures of Apertus 1.0: we respect opt-outs retroactively, use no paywalled or private sources, remove personally identifiable information and toxic text, train with the Goldfish objective to limit verbatim memorization, and publish the provenance of every dataset (Section 3.1.1, Section 3.2).
Open weights can be finetuned to remove the safety behavior of Section 5.9, and released models can be misused at scale. We address this with alignment trained into the released checkpoints, the acceptable-use policy (Section 7.1), the data-protection request channel, and pre-release evaluation by external organizations (Section 7.4); Section 7.2 reports the measured safety limitations.
7.4 Community and External Evaluation
Beyond releasing weights, data, and recipes (Section 7.3), we open the development process to outside contributors: an outreach and community function connects external contributors and deployment engineers with the development process and collects their findings to improve model compatibility. Smith et al. (2026) argue that inclusive design and capacity building are conditions for responsible openness. The public website1313
13
https://apertus-ai.org includes the charter, usage guides, benchmark resources, m