# Qwen3.8-Flash-Next vs Sakana Fugu-Ultra

> Side-by-side benchmark comparison for Qwen3.8-Flash-Next and Sakana Fugu-Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-8-flash-next-vs-sakana-fugu-ultra
- Last updated: October 10, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Sakana Fugu-Ultra leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Sakana Fugu-Ultra has the higher overall point estimate 77 to 64.23. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in multimodal & grounded, where the averages are 87.7 for Qwen3.8-Flash-Next and 77.1 for Sakana Fugu-Ultra.
- The biggest single benchmark swing is HLE w/o tools in Knowledge, with scores of 35.9% and 50%.
- Sakana Fugu-Ultra is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Sakana Fugu-Ultra also has the larger context window at 1M.

## Model Snapshot

| Property | Qwen3.8-Flash-Next | Sakana Fugu-Ultra |
|----------|----------|----------|
| Creator | Alibaba | Sakana AI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1M |
| Overall Score | 64.23 | null |
| Benchmarks Covered | 24 | 11 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 59.5 (Estimated · #24/123)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| CoWorkBench | 73.9% | Coming soon | Coming soon |
| JobBench | 55.7% | Coming soon | Coming soon |
| Agents' Last Exam | 51.2% | Coming soon | Coming soon |
| Toolathlon-Verified | 73.5% | Coming soon | Coming soon |
| AndroidWorld | 84.5% | Coming soon | Coming soon |
| OSWorld 2.0 | 19.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 82.1% | Coming soon |

### Coding

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 52.4 (Supported · #37/146)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 62.5% | 73.7% | Sakana Fugu-Ultra |
| SWE Multilingual | 81% | Coming soon | Coming soon |
| NL2Repo | 48.1% | Coming soon | Coming soon |
| DeepSWE | 58.7% | Coming soon | Coming soon |
| LiveCodeBench v6 | 91.9% | 93.2% | Sakana Fugu-Ultra |
| Terminal-Bench 2.1 | Coming soon | 82.1% | Coming soon |
| LiveCodeBench Pro | Coming soon | 90.8% | Coming soon |
| SciCode | Coming soon | 58.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 80.9 (Unranked · 2 rankable rows)
- Sakana Fugu-Ultra public-lane score: 84.4 (Unranked · 1 rankable row)

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | Coming soon | 93.6% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 87.7 (#8/54)
- Sakana Fugu-Ultra public-lane score: 77.1 (Unranked · 1 rankable row)

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| Vision2Web | 64.0% | Coming soon | Coming soon |
| ERQA | 72.3% | Coming soon | Coming soon |
| LVBench | 76.6% | Coming soon | Coming soon |
| RealWorldQA | 88.5% | Coming soon | Coming soon |
| MathVision | 90.6% | Coming soon | Coming soon |
| MathVision w/ Python | 95.7% | Coming soon | Coming soon |
| CharXiv w/o tools | 84.6% | Coming soon | Coming soon |
| CharXiv | 90.6% | 86.6% | Qwen3.8-Flash-Next |

### Knowledge

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 59.4 (Supported · #47/177)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 91.7% | 95.5% | Sakana Fugu-Ultra |
| GPQA-D | 91.7% | 95.5% | Sakana Fugu-Ultra |
| HLE | 35.9% | Coming soon | Coming soon |
| HLE w/o tools | 35.9% | 50% | Sakana Fugu-Ultra |

### Instruction Following

- Winner: Not comparable
- Qwen3.8-Flash-Next public-lane score: 91.2 (#22/127)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Qwen3.8-Flash-Next | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 81.3% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Qwen3.8-Flash-Next or Sakana Fugu-Ultra?

Sakana Fugu-Ultra has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Qwen3.8-Flash-Next and Sakana Fugu-Ultra?

The widest category gap is in multimodal & grounded, where the averages are 87.7 for Qwen3.8-Flash-Next and 77.1 for Sakana Fugu-Ultra.

### How many benchmarks does Qwen3.8-Flash-Next cover on BenchLM?

Qwen3.8-Flash-Next currently has 24 sourced benchmark scores on BenchLM.

### How many benchmarks does Sakana Fugu-Ultra cover on BenchLM?

Sakana Fugu-Ultra currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Qwen3.8-Flash-Next vs Sakana Fugu](/compare/qwen3-8-flash-next-vs-sakana-fugu)
- [Sakana Fugu-Ultra vs Sakana Fugu](/compare/sakana-fugu-vs-sakana-fugu-ultra)
- [Qwen3.8-Flash-Next vs Fugu Cyber](/compare/qwen3-8-flash-next-vs-sakana-fugu-cyber)
- [Sakana Fugu-Ultra vs Fugu Cyber](/compare/sakana-fugu-cyber-vs-sakana-fugu-ultra)

## Explore More

- [Qwen3.8-Flash-Next profile](/models/qwen3-8-flash-next)
- [Sakana Fugu-Ultra profile](/models/sakana-fugu-ultra)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)