# Fugu Usage, Cost & Rank | OpenCode Data

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

- Page: https://opencode.ai/data/sakana/fugu
- JSON: https://opencode.ai/data/sakana/fugu.json
- Model ID: sakana/fugu
- Lab: Sakana

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 1M |
| Max output | - |
| Knowledge cutoff | - |
| Release date | 2026-06-15 |
| Input modalities | text, image |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | No |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE Bench Pro | 59 |  | https://console.sakana.ai/models |
| Terminal Bench 2.1 | 80.2 |  | https://console.sakana.ai/models |
| LiveCodeBench | 92.9 |  | https://console.sakana.ai/models |
| LiveCodeBench Pro | 87.8 |  | https://console.sakana.ai/models |
| Humanity’s Last Exam | 47.2 |  | https://console.sakana.ai/models |
| CharXiv Reasoning | 85.1 |  | https://console.sakana.ai/models |
| GPQA Diamond | 95.5 |  | https://console.sakana.ai/models |
| SciCode | 60.1 |  | https://console.sakana.ai/models |
| τ3 Banking | 21.7 |  | https://console.sakana.ai/models |
| Long Context Reasoning | 74.7 |  | https://console.sakana.ai/models |
| MRCRv2 | 86.6 |  | https://console.sakana.ai/models |
| CTI-REALM | 67.5 |  | https://console.sakana.ai/models |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.