# Gemini 3.5 Flash-Lite vs Sakana Fugu-Ultra

> Side-by-side benchmark comparison for Gemini 3.5 Flash-Lite and Sakana Fugu-Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-3-5-flash-lite-vs-sakana-fugu-ultra
- Last updated: September 4, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Sakana Fugu-Ultra if you want the stronger benchmark profile. Gemini 3.5 Flash-Lite only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Sakana Fugu-Ultra leads overall 77 to 60.5.
- The clearest category separation is in reasoning, where the averages are 60.8 for Gemini 3.5 Flash-Lite and 77.9 for Sakana Fugu-Ultra.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 54% and 82.1%.
- Sakana Fugu-Ultra is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra |
|----------|----------|----------|
| Creator | Google | Sakana AI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 60.5 | null |
| Benchmarks Covered | 10 | 11 |
| Pricing (input/output) | $0.30 / $2.50 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 43.4 (Estimated · #104/151)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 54% | 82.1% | Sakana Fugu-Ultra |
| OSWorld-Verified | 74% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 50.2% | Coming soon | Coming soon |

### Coding

- Winner: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 43.6 (Supported · #121/183)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 54.0% | 82.1% | Sakana Fugu-Ultra |
| SWE-bench Pro | 54.2% | 73.7% | Sakana Fugu-Ultra |
| LiveCodeBench (Vals) | 79.0% | Coming soon | Coming soon |
| SWE-bench (Vals) | 75.0% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 93.2% | Coming soon |
| LiveCodeBench Pro | Coming soon | 90.8% | Coming soon |
| SciCode | Coming soon | 58.7% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 76.1 (#16/48)
- Sakana Fugu-Ultra public-lane score: 72.5 (Unranked · 1 rankable row)

| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | Coming soon | 86.6% | Coming soon |

### Reasoning

- Winner: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 60.8 (Unranked · 3 rankable rows)
- Sakana Fugu-Ultra public-lane score: 77.9 (Unranked · 1 rankable row)

| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | 72.2% | 93.6% | Sakana Fugu-Ultra |

### Knowledge

- Winner: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 53 (Supported · #71/181)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 83.8% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 85.8% | Coming soon | Coming soon |
| GPQA | Coming soon | 95.5% | Coming soon |
| GPQA-D | Coming soon | 95.5% | Coming soon |
| HLE w/o tools | Coming soon | 50% | Coming soon |

## FAQ

### Which is better overall, Gemini 3.5 Flash-Lite or Sakana Fugu-Ultra?

Sakana Fugu-Ultra is ahead overall on BenchLM right now.

### Where is the biggest gap between Gemini 3.5 Flash-Lite and Sakana Fugu-Ultra?

The widest category gap is in reasoning, where the averages are 60.8 for Gemini 3.5 Flash-Lite and 77.9 for Sakana Fugu-Ultra.

### How many benchmarks does Gemini 3.5 Flash-Lite cover on BenchLM?

Gemini 3.5 Flash-Lite currently has 10 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

- [Gemini 3.5 Flash-Lite vs Sakana Fugu](/compare/gemini-3-5-flash-lite-vs-sakana-fugu)
- [Sakana Fugu-Ultra vs Sakana Fugu](/compare/sakana-fugu-vs-sakana-fugu-ultra)
- [Gemini 3.5 Flash-Lite vs Fugu Cyber](/compare/gemini-3-5-flash-lite-vs-sakana-fugu-cyber)
- [Sakana Fugu-Ultra vs Fugu Cyber](/compare/sakana-fugu-cyber-vs-sakana-fugu-ultra)

## Explore More

- [Gemini 3.5 Flash-Lite profile](/models/gemini-3-5-flash-lite)
- [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)