Model comparison
Gemma 4 12B vs Sakana Fugu-Ultra
Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Gemma 4 12B #137 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Gemma 4 12B and Sakana Fugu-Ultra share 4 comparable benchmark results. 3 of 8 categories are comparable. 19 results are unique to Gemma 4 12B; 7 to Sakana Fugu-Ultra.
Updated July 23, 2026- Shared results
- 4
- Gemma 4 12B only
- 19
- Sakana Fugu-Ultra only
- 7
- Comparable categories
- 3 / 8
Treat this as a split decision. Gemma 4 12B makes more sense if its workflow fits your team better; Sakana Fugu-Ultra is the better fit if reasoning is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 2 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
Gemma 4 12B 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.
Sakana Fugu-Ultra gives you the larger context window at 1M, compared with 256K for Gemma 4 12B.
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 | Gemma 4 12B | Δ | Sakana Fugu-Ultra |
|---|---|---|---|
| Reasoning | Gemma 4 12B43.4 | Margin→ 50.2 | Sakana Fugu-Ultra93.6 |
| Knowledge | Gemma 4 12B77.5 | Margin→ 18.0 | Sakana Fugu-Ultra95.5 |
| Multimodal | Gemma 4 12B69.1 | Margin→ 17.5 | Sakana Fugu-Ultra86.6 |
| Agentic | Gemma 4 12BNot measured | MarginNo overlap | Sakana Fugu-Ultra82.1 |
| Coding | Gemma 4 12BNot measured | MarginNo overlap | Sakana Fugu-Ultra64.5 |
| Math | Gemma 4 12B77.5 | MarginNo overlap | Sakana Fugu-UltraNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
MRCRv2
ReasoningA 43.4%B 93.6%Winner: Sakana Fugu-UltraΔ 50.2MRCRv2: Gemma 4 12B scored 43.4%; Sakana Fugu-Ultra scored 93.6%. Sakana Fugu-Ultra wins this benchmark. - Source ↗
GPQA
KnowledgeA 78.8%B 95.5%Winner: Sakana Fugu-UltraΔ 16.7GPQA: Gemma 4 12B scored 78.8%; Sakana Fugu-Ultra scored 95.5%. Sakana Fugu-Ultra wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemma 4 12B | Sakana Fugu-Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemma 4 12BNot available | Sakana Fugu-UltraNot available | A complete price comparison is not available. |
| Generation speedtokens per second | Gemma 4 12BNot available | Sakana Fugu-UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Gemma 4 12BNot available | Sakana Fugu-UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Gemma 4 12B256K | Sakana Fugu-Ultra1M | Sakana Fugu-Ultra lists the larger context window. |
Benchmark Deep Dive
Agentic2 benchmarks
Coding6 benchmarks
ReasoningSakana Fugu-Ultra wins4 benchmarks
KnowledgeSakana Fugu-Ultra wins11 benchmarks
| Benchmark | Gemma 4 12B | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| GPQASource | 78.8% | 95.5% | Sakana Fugu-Ultra leads |
| GPQA-DSource | 78.8% | 95.5% | Sakana Fugu-Ultra leads |
| MMLU-ProSource | 77.2% | — | Not comparable |
| HLE w/o toolsSource | 5.2% | 50% | Sakana Fugu-Ultra leads |
| MMMLUSource | 83.4% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 22.0% | — | Not comparable |
| AA-GPQA DiamondSource | 75.3% | — | Not comparable |
| AA-HLESource | 14.8% | — | Not comparable |
| AA-Omniscience IndexSource | -51.9% | — | Not comparable |
| AA-Omniscience AccuracySource | 16.0% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 80.8% | — | Not comparable |
Math1 benchmarks
| Benchmark | Gemma 4 12B | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| AIME26Source | 77.5% | — | Not comparable |
MultimodalSakana Fugu-Ultra wins5 benchmarks
Inst. Following1 benchmarks
| Benchmark | Gemma 4 12B | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.5% | — | Not comparable |
Frequently Asked Questions (4)
Which is better, Gemma 4 12B or Sakana Fugu-Ultra?
Gemma 4 12B 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 knowledge tasks, Gemma 4 12B or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 77.5. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
Which is better for reasoning, Gemma 4 12B or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for reasoning in this comparison, averaging 93.6 versus 43.4. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Gemma 4 12B or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 69.1. Gemma 4 12B stays close enough that the answer can still flip depending on your workload.
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.