OpenThinkerAgent-32B-SFT-316
OpenThoughts-Agent is an open-source effort to curate the best datasets for training agents. Our release includes datasets, models and our research codebase.
OpenThinkerAgent-32B-SFT-316 is post-trained from Qwen/Qwen3-32B with full-parameter SFT on the 316-example OpenThoughts-Agent-SFT-316 dataset (Top-4 task sources, GLM-4.7-AWQ teacher in the terminus-2 harness, ≥5-turn trace filter).
- Homepage: https://www.openthoughts.ai/blog/agent
- Repository: https://github.com/open-thoughts/OpenThoughts-Agent
Performance
Evaluated in the terminus-2 harness (pass@1, mean over 3 stochastic re-runs):
| Model | Harness | SWE-Bench-Verified-100 | OpenThoughts-TBLite | Terminal-Bench 2.0 |
|---|---|---|---|---|
| Qwen/Qwen3-32B | Terminus-2 | 26.7 | 13.7 | 7.5 |
| OpenThinkerAgent-32B-SFT-316 | Terminus-2 | 16.3 | 24.2 | 13.1 |
Data
The model is trained on OpenThoughts-Agent-SFT-316: (task, agent-trajectory) pairs from the Top-4 task sources (SWE-Smith, StackExchange-SuperUser, StackExchange-Tezos with synthetic augmentation, IssueTasks). Trajectories are generated by GLM-4.7-AWQ in the terminus-2 harness and filtered to traces with at least 5 model turns.
Training hyperparameters
- learning_rate: 4e-05
- lr_scheduler_type: cosine, warmup_ratio 0.1
- global_batch_size: 96
- num_epochs: 7
- cutoff_len: 32768
- precision: bf16, DeepSpeed ZeRO-3
Links
- 🌐 OpenThoughts-Agent project page
- 💻 OpenThoughts-Agent GitHub repository
- 📚 OpenThinker-Agent collection
- 🧠 Training dataset: OpenThoughts-Agent-SFT-316
Citation
@misc{openthoughts-agent,
author = {Team, OpenThoughts-Agent},
title = {{OpenThoughts-Agent: Data Recipes for Agentic Models}},
howpublished = {https://www.openthoughts.ai/blog/agent},
year = {2026}
}