Fugu Ultra
fugu
Quality-first multi-agent model for hard research, analysis, and competitions
ReasoningTool CallingAttachmentsStructured Output
Context Window
1M
Max Output
undefined
Temperature
No
Open Weights
No
Knowledge Cutoff
N/A
Released
2026-06-15
Last Updated
2026-06-15
Modalities
Input:TextImage
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| SWE Bench Pro | 73.7 | |
| Terminal Bench 2.1 | 82.1 | |
| LiveCodeBench | 93.2 | |
| LiveCodeBench Pro | 90.8 | |
| Humanity’s Last Exam | 50 | |
| CharXiv Reasoning | 86.6 | |
| GPQA Diamond | 95.5 | |
| SciCode | 58.7 | |
| τ3 Banking | 20.6 | |
| Long Context Reasoning | 73.3 | |
| MRCRv2 | 93.6 | |
| CTI-REALM | 69.4 |
Links
Available Providers (2)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 Vercel AI Gateway | Rp 89.482 | Rp 536.890 | Rp 8.949 | — | ✓ | — |
 OpenRouter | Rp 89.482 | Rp 536.890 | Rp 8.949 | — | effort | — |