BFCL
Function-calling benchmark (SmolLM3 card; version not stated)
agents and tool use
Definition
- Version
- not in the notes
- Category
- agents and tool use
- Maintainer
- not in the notes
- Status
- not in the notes
- Home page
- not in the notes
Sources
- HuggingFaceTB/SmolLM3-3B , Hugging Face huggingface.co https://huggingface.co/HuggingFaceTB/SmolLM3-3B
Scores at a Glance
Score in %
Higher is better for this unit.
1
SmolLM3-3BHugging FaceCard 5-model comparison table; mode label not extracted
Jamba 1.5 MiniAI21 Labs
SmolLM3-3BHugging FaceCard 5-model comparison table; mode label not extracted92.3 %
vendor-reported2Jamba 1.5 MiniAI21 Labs80.6 %
vendor-reported0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| SmolLM3-3B | 92.3 % | vendor-reported | Card 5-model comparison table; mode label not extracted | – | – | huggingface.co |
 GLM-4 (0520) | 81.76 score | vendor-reported | Berkeley Function Call overall | – | 18 Jun 2024 | arxiv.org |
| Jamba 1.5 Mini | 80.6 % | vendor-reported | – | – | Aug 2024 | huggingface.co |
 Granite-4.0-H-Micro | 57.56 % | vendor-reported | BFCL v3 | Granite-4.0-H-Micro model card | 2 Oct 2025 | huggingface.co |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BFCL", https://aurion.semai.id/benchmarks/bfcl/, records of October 2026.