# Sakana Fugu-Ultra vs Step 3.7 Flash

> Side-by-side benchmark comparison for Sakana Fugu-Ultra and Step 3.7 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/sakana-fugu-ultra-vs-step-3-7-flash
- Last updated: September 28, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Evidence is too thin for a benchmark verdict: Sakana Fugu-Ultra and Step 3.7 Flash share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Sakana Fugu-Ultra has the lower published output-token price.
- Sakana Fugu-Ultra has the larger published context window at 1M.

## Model Snapshot

| Property | Sakana Fugu-Ultra | Step 3.7 Flash |
|----------|----------|----------|
| Creator | Sakana AI | StepFun |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 256K |
| Independent public score (not head-to-head) | null | 41.35 |
| Benchmarks Covered | 11 | 11 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | $0.20 / $1.15 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 35.6 (Estimated · #64/117)

| Benchmark | Sakana Fugu-Ultra | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 82.1% | 59.5% | Sakana Fugu-Ultra |
| BrowseComp | Coming soon | 75.8% | Coming soon |
| DeepSearchQA | Coming soon | 92.8% | Coming soon |
| Toolathlon | Coming soon | 49.5% | Coming soon |
| Claw-Eval | Coming soon | 67.1% | Coming soon |
| HLE w/ tools | Coming soon | 47.2% | Coming soon |
| Gert Labs | Coming soon | 51.57% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 32.2 (Estimated · #88/142)

| Benchmark | Sakana Fugu-Ultra | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 73.7% | 56.3% | Sakana Fugu-Ultra |
| Terminal-Bench 2.1 | 82.1% | 59.5% | Sakana Fugu-Ultra |
| LiveCodeBench v6 | 93.2% | Coming soon | Coming soon |
| LiveCodeBench Pro | 90.8% | Coming soon | Coming soon |
| SciCode | 58.7% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: 79.1 (Unranked · 1 rankable row)
- Step 3.7 Flash public-lane score: 73 (Unranked · 2 rankable rows)

| Benchmark | Sakana Fugu-Ultra | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | 93.6% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: 73.6 (Unranked · 1 rankable row)
- Step 3.7 Flash public-lane score: 72 (Unranked · 3 rankable rows)

| Benchmark | Sakana Fugu-Ultra | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 86.6% | Coming soon | Coming soon |
| SimpleVQA | Coming soon | 79.2% | Coming soon |
| V* | Coming soon | 95.3% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 43.2 (Estimated · #84/168)

| Benchmark | Sakana Fugu-Ultra | Step 3.7 Flash | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 95.5% | Coming soon | Coming soon |
| GPQA-D | 95.5% | Coming soon | Coming soon |
| HLE w/o tools | 50% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Sakana Fugu-Ultra public-lane score: Coming soon
- Step 3.7 Flash public-lane score: 80.6 (#53/124)

## FAQ

### Is there enough evidence to pick between Sakana Fugu-Ultra and Step 3.7 Flash?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Sakana Fugu-Ultra vs Sakana Fugu](/compare/sakana-fugu-vs-sakana-fugu-ultra)
- [Step 3.7 Flash vs Sakana Fugu](/compare/sakana-fugu-vs-step-3-7-flash)
- [Sakana Fugu-Ultra vs Fugu Cyber](/compare/sakana-fugu-cyber-vs-sakana-fugu-ultra)
- [Step 3.7 Flash vs Fugu Cyber](/compare/sakana-fugu-cyber-vs-step-3-7-flash)

## Explore More

- [Sakana Fugu-Ultra profile](/models/sakana-fugu-ultra)
- [Step 3.7 Flash profile](/models/step-3-7-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)