OpenAI: GPT-6.1 Sol vs Sakana: Fugu Max
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-30.
| OpenAI: GPT-6.1 Sol | Sakana: Fugu Max | |
|---|---|---|
| Vendor | openai | sakana |
| Quality Score | 100 | 100 |
| Benchmark Score | 89.2 | - |
| Input Price | $2.00/M | $2.00/M |
| Output Price | $10.00/M | $6.00/M |
| Context Window | 1,050,000 | 1,000,000 |
| Max Output | 128,000 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 85.5 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Fugu Max costs $3.50 and GPT-6.1 Sol costs $4.50, so Fugu Max is about 1.3 times cheaper for the same work.
Both take in a similar amount of text: 1,050,000 and 1,000,000 tokens, about 1,575 and 1,500 pages.
Across the 20 tasks where they differ, GPT-6.1 Sol scores higher on 18 (SQL Generation, Code Review, Code Completion and others), Fugu Max on 2 (JSON Extraction, Bulk Data Labeling).
Pick GPT-6.1 Sol if you need the stronger all-round task scores; pick Fugu Max if you need lower cost.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | OpenAI: GPT-6.1 Sol | Sakana: Fugu Max |
|---|---|---|
| SQL Generation | 143 | 133 |
| Code Review | 148 | 132 |
| Code Completion | 119 | 118 |
| Code Refactoring | 149 | 136 |
| Bug Fixing | 152 | 136 |
| Unit Test Generation | 134 | 124 |
| Code Documentation | 137 | 130 |
| Regex Writing | 126 | 118 |
| CI/CD Pipelines | 130 | 120 |
| Frontend Component Design | 132 | 122 |
| Data Analysis | 136 | 124 |
| CSV / Spreadsheet Cleanup | 136 | 133 |
| ETL Scripting | 140 | 128 |
| JSON Extraction | 121 | 122 |
| Bulk Data Labeling | 118 | 119 |
| OCR / Document Parsing | 135 | 131 |
| Table Extraction from PDFs | 135 | 131 |
| Long-Document Summarization | 150 | 137 |
| Short-Form Summarization | 117 | 114 |
| Blog Post Writing | 131 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →