# GPT-5.5 vs Sakana Fugu

> Side-by-side benchmark comparison for GPT-5.5 and Sakana Fugu across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-5-vs-sakana-fugu
- Last updated: September 27, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick GPT-5.5 if you want the stronger benchmark profile. Sakana Fugu only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- GPT-5.5 leads overall 69.13 to 65.
- The clearest category separation is in reasoning, where the averages are 65.9 for GPT-5.5 and 70.6 for Sakana Fugu.
- The biggest single benchmark swing is HLE w/o tools in Knowledge, with scores of 41.4% and 47.2%.
- Sakana Fugu is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | GPT-5.5 | Sakana Fugu |
|----------|----------|----------|
| Creator | OpenAI | Sakana AI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 69.13 | null |
| Benchmarks Covered | 39 | 11 |
| Pricing (input/output) | $5.00 / $30.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GPT-5.5 public-lane score: 60.1 (Supported · #15/105)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 82% | Coming soon | Coming soon |
| CyberGym | 81.8% | Coming soon | Coming soon |
| BrowseComp | 84.4% | Coming soon | Coming soon |
| OSWorld-Verified | 78.7% | Coming soon | Coming soon |
| MCP Atlas | 75.3% | Coming soon | Coming soon |
| Toolathlon | 55.6% | Coming soon | Coming soon |
| τ²-bench results | 98% | Coming soon | Coming soon |
| Gert Labs | 72.93% | Coming soon | Coming soon |
| ResearchClawBench | 17.0% | Coming soon | Coming soon |
| OSWorld 2.0 | 13.0% | Coming soon | Coming soon |
| JobBench | 42.7% | Coming soon | Coming soon |
| ExploitGym | 13.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 76.4% | Coming soon | Coming soon |
| ApprenticeBench | 20% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 80.2% | Coming soon |

### Coding

- Winner: Not comparable
- GPT-5.5 public-lane score: 64.1 (Supported · #11/135)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 58.6% | 59% | Sakana Fugu |
| Terminal-Bench 2.0 | 82.0% | Coming soon | Coming soon |
| Vibe Code Bench | 69.85% | Coming soon | Coming soon |
| React Native Evals | 84.7% | Coming soon | Coming soon |
| cursorBench31 | 59.2% | Coming soon | Coming soon |
| cursorBench32 | 58.4% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 43.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.3% | Coming soon | Coming soon |
| SWE-bench (Vals) | 82.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 80.2% | Coming soon |
| LiveCodeBench v6 | Coming soon | 92.9% | Coming soon |
| LiveCodeBench Pro | Coming soon | 87.8% | Coming soon |
| SciCode | Coming soon | 60.1% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.5 public-lane score: 65.9 (#10/19)
- Sakana Fugu public-lane score: 70.6 (Unranked · 1 rankable row)

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| MRCR v2 64K-128K | 83.1% | Coming soon | Coming soon |
| MRCR v2 128K-256K | 87.5% | Coming soon | Coming soon |
| ARC-AGI-2 | 85% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.4% | Coming soon | Coming soon |
| MRCRv2 | Coming soon | 86.6% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- GPT-5.5 public-lane score: 71.4 (#20/50)
- Sakana Fugu public-lane score: 68.6 (Unranked · 1 rankable row)

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 81.2% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 83.2% | Coming soon | Coming soon |
| OfficeQA Pro | 54.1% | Coming soon | Coming soon |
| CharXiv | Coming soon | 85.1% | Coming soon |

### Knowledge

- Winner: Not comparable
- GPT-5.5 public-lane score: 70 (Supported · #12/158)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 93.6% | 95.5% | Sakana Fugu |
| GPQA-D | 93.6% | 95.5% | Sakana Fugu |
| HLE | 52.2% | Coming soon | Coming soon |
| HLE w/o tools | 41.4% | 47.2% | Sakana Fugu |
| GPQA Diamond (Vals) | 93.2% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 88.1% | Coming soon | Coming soon |

### Instruction Following

- Winner: Not comparable
- GPT-5.5 public-lane score: 91.9 (#7/124)
- Sakana Fugu public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- GPT-5.5 public-lane score: 69.4 (Unranked · 3 rankable rows)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | GPT-5.5 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath (legacy) | 51.7% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 51.700% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 35.400% | Coming soon | Coming soon |

## FAQ

### Which is better overall, GPT-5.5 or Sakana Fugu?

GPT-5.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between GPT-5.5 and Sakana Fugu?

The widest category gap is in reasoning, where the averages are 65.9 for GPT-5.5 and 70.6 for Sakana Fugu.

### How many benchmarks does GPT-5.5 cover on BenchLM?

GPT-5.5 currently has 39 sourced benchmark scores on BenchLM.

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

Sakana Fugu currently has 11 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5.5 vs GPT-5.5 Pro](/compare/gpt-5-5-vs-gpt-5-5-pro)
- [Sakana Fugu vs GPT-5.5 Pro](/compare/gpt-5-5-pro-vs-sakana-fugu)
- [GPT-5.5 vs Sakana Fugu-Ultra](/compare/gpt-5-5-vs-sakana-fugu-ultra)
- [Sakana Fugu vs Sakana Fugu-Ultra](/compare/sakana-fugu-vs-sakana-fugu-ultra)

## Explore More

- [GPT-5.5 profile](/models/gpt-5-5)
- [Sakana Fugu profile](/models/sakana-fugu)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)