Model comparison
Gemini 3.5 Flash-Lite vs Sakana Fugu-Ultra
Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Evidence parity. Gemini 3.5 Flash-Lite and Sakana Fugu-Ultra share 4 comparable benchmark results. 3 of 8 categories are comparable. 17 results are unique to Gemini 3.5 Flash-Lite; 7 to Sakana Fugu-Ultra.
Updated July 21, 2026- Shared results
- 4
- Gemini 3.5 Flash-Lite only
- 17
- Sakana Fugu-Ultra only
- 7
- Comparable categories
- 3 / 8
Treat this as a split decision. Gemini 3.5 Flash-Lite makes more sense if its workflow fits your team better; Sakana Fugu-Ultra is the better fit if reasoning is the priority.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Gemini 3.5 Flash-Lite and Sakana Fugu-Ultra finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Gemini 3.5 Flash-Lite | Δ | Sakana Fugu-Ultra |
|---|---|---|---|
| Reasoning | Gemini 3.5 Flash-Lite72.2 | Margin→ 21.4 | Sakana Fugu-Ultra93.6 |
| Agentic | Gemini 3.5 Flash-Lite63.4 | Margin→ 18.7 | Sakana Fugu-Ultra82.1 |
| Coding | Gemini 3.5 Flash-Lite54.2 | Margin→ 10.3 | Sakana Fugu-Ultra64.5 |
| Knowledge | Gemini 3.5 Flash-LiteNot measured | MarginNo overlap | Sakana Fugu-Ultra95.5 |
| Multimodal | Gemini 3.5 Flash-LiteNot measured | MarginNo overlap | Sakana Fugu-Ultra86.6 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 54%B 82.1%Winner: Sakana Fugu-UltraΔ 28.1Terminal-Bench 2.0: Gemini 3.5 Flash-Lite scored 54%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark. - Source ↗
MRCRv2
ReasoningA 72.2%B 93.6%Winner: Sakana Fugu-UltraΔ 21.4MRCRv2: Gemini 3.5 Flash-Lite scored 72.2%; Sakana Fugu-Ultra scored 93.6%. Sakana Fugu-Ultra wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 54.2%B 73.7%Winner: Sakana Fugu-UltraΔ 19.5SWE-bench Pro: Gemini 3.5 Flash-Lite scored 54.2%; Sakana Fugu-Ultra scored 73.7%. Sakana Fugu-Ultra wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemini 3.5 Flash-Lite$0.3 input / $2.5 output | Sakana Fugu-UltraNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Gemini 3.5 Flash-LiteNot available | Sakana Fugu-UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Gemini 3.5 Flash-LiteNot available | Sakana Fugu-UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Gemini 3.5 Flash-Lite1M | Sakana Fugu-Ultra1M | Listed context windows are equal. |
Benchmark Deep Dive
AgenticSakana Fugu-Ultra wins7 benchmarks
| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 54% | 82.1% | Sakana Fugu-Ultra leads |
| OSWorld-VerifiedSource | 74% | — | Not comparable |
| GDPval-AASource | 1140 | — | Not comparable |
| AA Agentic IndexSource | 26.8% | — | Not comparable |
| GDPval-AASource | 32.0% | — | Not comparable |
| AA BriefcaseSource | 634 | — | Not comparable |
| AA Tau3 BankingSource | 16.5% | — | Not comparable |
CodingSakana Fugu-Ultra wins7 benchmarks
| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 54.0% | 82.1% | Sakana Fugu-Ultra leads |
| SWE-bench ProSource | 54.2% | 73.7% | Sakana Fugu-Ultra leads |
| AA Coding IndexSource | 49.3% | — | Not comparable |
| AA-SciCodeSource | 40.9% | — | Not comparable |
| LiveCodeBench v6Source | — | 93.2% | Not comparable |
| LiveCodeBench ProSource | — | 90.8% | Not comparable |
| SciCodeSource | — | 58.7% | Not comparable |
ReasoningSakana Fugu-Ultra wins3 benchmarks
Knowledge9 benchmarks
| Benchmark | Gemini 3.5 Flash-Lite | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 36.5% | — | Not comparable |
| AA-GPQA DiamondSource | 83.8% | — | Not comparable |
| AA-HLESource | 17.5% | — | Not comparable |
| AA-Omniscience IndexSource | 6.9% | — | Not comparable |
| AA-Omniscience AccuracySource | 30.3% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 33.5% | — | Not comparable |
| GPQASource | — | 95.5% | Not comparable |
| GPQA-DSource | — | 95.5% | Not comparable |
| HLE w/o toolsSource | — | 50% | Not comparable |
Frequently Asked Questions (4)
Which is better, Gemini 3.5 Flash-Lite or Sakana Fugu-Ultra?
Gemini 3.5 Flash-Lite and Sakana Fugu-Ultra are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, Gemini 3.5 Flash-Lite or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for coding in this comparison, averaging 64.5 versus 54.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for reasoning, Gemini 3.5 Flash-Lite or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for reasoning in this comparison, averaging 93.6 versus 72.2. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Gemini 3.5 Flash-Lite or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 63.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.