Model
Fugu
Multi-agent model for routing expert agents across complex analytical tasks
1 providers · 1 listingsreleased closed weights
—
no listed price
1M
context window
1M
max output
Compare providers (sorted by listed input price)
Benchmarks
- SWE Bench Pro ↗report ↗Unclassified source59
- Terminal Bench 2.1 ↗report ↗Unclassified source80.2
- LiveCodeBench ↗report ↗Unclassified source92.9
- LiveCodeBench Pro ↗report ↗Unclassified source87.8
- Humanity’s Last Exam ↗report ↗Unclassified source47.2
- CharXiv Reasoningreport ↗Unclassified source85.1
- GPQA Diamond ↗report ↗Unclassified source95.5
- SciCodereport ↗Unclassified source60.1
- τ3 Bankingreport ↗Unclassified source21.7
- Long Context Reasoningreport ↗Unclassified source74.7
- MRCRv2report ↗Unclassified source86.6
- CTI-REALMreport ↗Unclassified source67.5
Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.