ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
2 models
Sakana
Ranked by SciCode
Sakana: Fugu T
Reasoning Tools JSON 60.1

Multi-agent model for routing expert agents across complex analytical tasks

sakana/fugu 2026-06-15 1M context Input not listed Output not listed
1 provider
Sakana: Fugu Ultra T
Reasoning Tools JSON 58.7

Quality-first multi-agent model for hard research, analysis, and competitions

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output
11 providers