# GPT-5.6 Luna vs Sakana Fugu-Ultra

> Side-by-side benchmark comparison for GPT-5.6 Luna and Sakana Fugu-Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-6-luna-vs-sakana-fugu-ultra
- Last updated: September 28, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Sakana Fugu-Ultra if you want the stronger benchmark profile. GPT-5.6 Luna 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 74 to 65.55.
- The clearest category separation is in reasoning, where the averages are 55.8 for GPT-5.6 Luna and 79.1 for Sakana Fugu-Ultra.
- The biggest single benchmark swing is SWE-bench Pro in Coding, with scores of 62.7% and 73.7%.
- Sakana Fugu-Ultra is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.6 Luna also has the larger context window at 1.05M.

## Model Snapshot

| Property | GPT-5.6 Luna | Sakana Fugu-Ultra |
|----------|----------|----------|
| Creator | OpenAI | Sakana AI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1.05M | 1M |
| Overall Score | 65.55 | null |
| Benchmarks Covered | 30 | 11 |
| Pricing (input/output) | $0.20 / $1.20 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 55.2 (Supported · #33/117)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 14.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 84.7% | 82.1% | GPT-5.6 Luna |
| BrowseComp | 83.3% | Coming soon | Coming soon |
| OSWorld 2.0 | 45.6% | Coming soon | Coming soon |
| CyberGym | 77.9% | Coming soon | Coming soon |
| ExploitGym | 12.4% | Coming soon | Coming soon |
| Toolathlon | 53.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 79.0% | Coming soon | Coming soon |
| ApprenticeBench | 7% | Coming soon | Coming soon |

### Coding

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 63.1 (Supported · #11/142)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 62.7% | 73.7% | Sakana Fugu-Ultra |
| Terminal-Bench 2.1 | 84.7% | 82.1% | GPT-5.6 Luna |
| DeepSWE | 67.2% | Coming soon | Coming soon |
| FrontierCode 1.1 Extended | 55.1% | Coming soon | Coming soon |
| cursorBench32 | 61.1% | Coming soon | Coming soon |
| VulcanBench v3 | 85.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 93.0% | Coming soon | Coming soon |
| cursorBench40 | 35.9% | 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 |

### Reasoning

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 55.8 (#24/27)
- Sakana Fugu-Ultra public-lane score: 79.1 (Unranked · 1 rankable row)

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 59.5% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.2% | Coming soon | Coming soon |
| MRCRv2 | Coming soon | 93.6% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 68.1 (#22/50)
- Sakana Fugu-Ultra public-lane score: 73.6 (Unranked · 1 rankable row)

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 78.4% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 79.5% | Coming soon | Coming soon |
| CharXiv | Coming soon | 86.6% | Coming soon |

### Knowledge

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 64.7 (Supported · #25/168)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.3% | 95.5% | Sakana Fugu-Ultra |
| GPQA-D | 92.3% | 95.5% | Sakana Fugu-Ultra |
| HealthBench Professional | 55.7% | Coming soon | Coming soon |
| HealthBench Hard | 32.0% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 91.7% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.0% | Coming soon | Coming soon |
| HLE w/o tools | Coming soon | 50% | Coming soon |

### Mathematics

- Winner: Not comparable
- GPT-5.6 Luna public-lane score: 94.2 (Unranked · 3 rankable rows)
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | GPT-5.6 Luna | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath (legacy) | 78.6% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 78.600% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 58.500% | Coming soon | Coming soon |

## FAQ

### Which is better overall, GPT-5.6 Luna or Sakana Fugu-Ultra?

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

### Where is the biggest gap between GPT-5.6 Luna and Sakana Fugu-Ultra?

The widest category gap is in reasoning, where the averages are 55.8 for GPT-5.6 Luna and 79.1 for Sakana Fugu-Ultra.

### How many benchmarks does GPT-5.6 Luna cover on BenchLM?

GPT-5.6 Luna currently has 30 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

- [GPT-5.6 Luna vs GPT-5.6 Sol](/compare/gpt-5-6-luna-vs-gpt-5-6-sol)
- [Sakana Fugu-Ultra vs GPT-5.6 Sol](/compare/gpt-5-6-sol-vs-sakana-fugu-ultra)
- [GPT-5.6 Luna vs GPT-5.6 Terra](/compare/gpt-5-6-luna-vs-gpt-5-6-terra)
- [Sakana Fugu-Ultra vs GPT-5.6 Terra](/compare/gpt-5-6-terra-vs-sakana-fugu-ultra)

## Explore More

- [GPT-5.6 Luna profile](/models/gpt-5-6-luna)
- [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)