Model comparison
GPT-5.4 mini vs Sakana Fugu-Ultra
Head-to-head evidence from 3 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 mini #75 (Estimated); Sakana Fugu-Ultra unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 mini and Sakana Fugu-Ultra share 3 comparable benchmark results. 3 of 8 categories are comparable. 27 results are unique to GPT-5.4 mini; 8 to Sakana Fugu-Ultra.
Updated July 23, 2026- Shared results
- 3
- GPT-5.4 mini only
- 27
- Sakana Fugu-Ultra only
- 8
- Comparable categories
- 3 / 8
Treat this as a split decision. GPT-5.4 mini makes more sense if its workflow fits your team better; Sakana Fugu-Ultra is the better fit if knowledge is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 3 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
GPT-5.4 mini 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 400K for GPT-5.4 mini.
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 | GPT-5.4 mini | Δ | Sakana Fugu-Ultra |
|---|---|---|---|
| Knowledge | GPT-5.4 mini47.8 | Margin→ 47.7 | Sakana Fugu-Ultra95.5 |
| Agentic | GPT-5.4 mini65.7 | Margin→ 16.4 | Sakana Fugu-Ultra82.1 |
| Multimodal | GPT-5.4 mini76.6 | Margin→ 10.0 | Sakana Fugu-Ultra86.6 |
| Coding | GPT-5.4 miniNot measured | MarginNo overlap | Sakana Fugu-Ultra64.5 |
| Reasoning | GPT-5.4 miniNot measured | MarginNo overlap | Sakana Fugu-Ultra93.6 |
| Math | GPT-5.4 mini21.7 | MarginNo overlap | Sakana Fugu-UltraNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 60%B 82.1%Winner: Sakana Fugu-UltraΔ 22.1Terminal-Bench 2.0: GPT-5.4 mini scored 60%; Sakana Fugu-Ultra scored 82.1%. Sakana Fugu-Ultra wins this benchmark. - Source ↗
GPQA
KnowledgeA 88%B 95.5%Winner: Sakana Fugu-UltraΔ 7.5GPQA: GPT-5.4 mini scored 88%; 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 | GPT-5.4 mini | Sakana Fugu-Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4 mini$0.75 input / $4.5 output | Sakana Fugu-UltraNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.4 mini201 tok/s | Sakana Fugu-UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4 mini3.85 s | Sakana Fugu-UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.4 mini400K | Sakana Fugu-Ultra1M | Sakana Fugu-Ultra lists the larger context window. |
Benchmark Deep Dive
AgenticSakana Fugu-Ultra wins9 benchmarks
| Benchmark | GPT-5.4 mini | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 60% | 82.1% | Sakana Fugu-Ultra leads |
| OSWorld-VerifiedSource | 72.1% | — | Not comparable |
| MCP AtlasSource | 57.7% | — | Not comparable |
| ToolathlonSource | 42.9% | — | Not comparable |
| τ²-bench resultsSource | 83.3% | — | Not comparable |
| AA Agentic IndexSource | 30.2% | — | Not comparable |
| APEX-Agents-AASource | 28.2% | — | Not comparable |
| GDPval-AASource | 33.6% | — | Not comparable |
| GDPval-AASource | 1171 | — | Not comparable |
Coding9 benchmarks
| Benchmark | GPT-5.4 mini | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| Vibe Code BenchSource | 47.97% | — | Not comparable |
| AA Coding IndexSource | 56.1% | — | Not comparable |
| AA-SciCodeSource | 49.9% | — | Not comparable |
| FrontierCode 1.1 MainSource | 27.0% | — | Not comparable |
| SWE-bench ProSource | — | 73.7% | Not comparable |
| Terminal-Bench 2.0Source | — | 82.1% | Not comparable |
| LiveCodeBench v6Source | — | 93.2% | Not comparable |
| LiveCodeBench ProSource | — | 90.8% | Not comparable |
| SciCodeSource | — | 58.7% | Not comparable |
Reasoning3 benchmarks
KnowledgeSakana Fugu-Ultra wins10 benchmarks
| Benchmark | GPT-5.4 mini | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| GPQASource | 88% | 95.5% | Sakana Fugu-Ultra leads |
| HLESource | 41.5% | — | Not comparable |
| HLE w/o toolsSource | 28.2% | 50% | Sakana Fugu-Ultra leads |
| Artificial Analysis Intelligence IndexSource | 40.0% | — | Not comparable |
| AA-GPQA DiamondSource | 87.5% | — | Not comparable |
| AA-HLESource | 26.6% | — | Not comparable |
| AA-Omniscience IndexSource | -18.7% | — | Not comparable |
| AA-Omniscience AccuracySource | 37.5% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 89.8% | — | Not comparable |
| GPQA-DSource | — | 95.5% | Not comparable |
Math2 benchmarks
MultimodalSakana Fugu-Ultra wins4 benchmarks
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 mini | Sakana Fugu-Ultra | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.3% | — | Not comparable |
Frequently Asked Questions (4)
Which is better, GPT-5.4 mini or Sakana Fugu-Ultra?
GPT-5.4 mini 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, GPT-5.4 mini or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for knowledge tasks in this comparison, averaging 95.5 versus 47.8. Inside this category, HLE w/o tools is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 mini or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for agentic tasks in this comparison, averaging 82.1 versus 65.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.4 mini or Sakana Fugu-Ultra?
Sakana Fugu-Ultra has the edge for multimodal and grounded tasks in this comparison, averaging 86.6 versus 76.6. GPT-5.4 mini 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.