# Muse Spark 1.1 vs Sakana Fugu

> Side-by-side benchmark comparison for Muse Spark 1.1 and Sakana Fugu across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/muse-spark-1-1-vs-sakana-fugu
- Last updated: October 7, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Sakana Fugu if you want the stronger benchmark profile. Muse Spark 1.1 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Sakana Fugu leads overall 67 to 65.95.
- The clearest category separation is in multimodal & grounded, where the averages are 78.3 for Muse Spark 1.1 and 69.6 for Sakana Fugu.
- The biggest single benchmark swing is HLE w/o tools in Knowledge, with scores of 52.2% and 47.2%.

## Model Snapshot

| Property | Muse Spark 1.1 | Sakana Fugu |
|----------|----------|----------|
| Creator | Meta | Sakana AI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 65.95 | null |
| Benchmarks Covered | 26 | 11 |
| Pricing (input/output) | N/A | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Muse Spark 1.1 public-lane score: 56.9 (Supported · #32/122)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | Muse Spark 1.1 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 80.0% | 80.2% | Sakana Fugu |
| MCP Atlas | 88.1% | Coming soon | Coming soon |
| Toolathlon | 75.6% | Coming soon | Coming soon |
| OSWorld-Verified | 80.8% | Coming soon | Coming soon |
| WebArena-Verified | 69% | Coming soon | Coming soon |
| DeepSearchQA | 84.9% | Coming soon | Coming soon |
| CyberGym | 59.0% | Coming soon | Coming soon |
| Finance Agent v2 | 57.2% | Coming soon | Coming soon |
| deepSwe | 53.3% | Coming soon | Coming soon |
| OSWorld 2.0 | 14.2% | Coming soon | Coming soon |
| JobBench | 54.7% | Coming soon | Coming soon |
| Cybench | 92.9% | Coming soon | Coming soon |
| ExploitGym | 0.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 69.3% | Coming soon | Coming soon |

### Coding

- Winner: Not comparable
- Muse Spark 1.1 public-lane score: 54.2 (Supported · #35/146)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | Muse Spark 1.1 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 80.0% | 80.2% | Sakana Fugu |
| SWE-bench Pro | 61.5% | 59% | Muse Spark 1.1 |
| LiveCodeBench (Vals) | 85.9% | Coming soon | Coming soon |
| SWE-bench (Vals) | 82.0% | Coming soon | 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
- Muse Spark 1.1 public-lane score: 75.7 (Unranked · 3 rankable rows)
- Sakana Fugu public-lane score: 70.7 (Unranked · 1 rankable row)

| Benchmark | Muse Spark 1.1 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 54.1% | Coming soon | Coming soon |
| MRCRv2 | Coming soon | 86.6% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Muse Spark 1.1 public-lane score: 78.3 (Unranked · 2 rankable rows)
- Sakana Fugu public-lane score: 69.6 (Unranked · 1 rankable row)

| Benchmark | Muse Spark 1.1 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 88.4% | 85.1% | Muse Spark 1.1 |
| BabyVision | 76.3% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- Muse Spark 1.1 public-lane score: 66.7 (Supported · #21/174)
- Sakana Fugu public-lane score: Coming soon

| Benchmark | Muse Spark 1.1 | Sakana Fugu | Winner |
|-----------|-----------|-----------|--------|
| HLE | 62.1% | Coming soon | Coming soon |
| HLE w/o tools | 52.2% | 47.2% | Muse Spark 1.1 |
| HealthBench Professional | 59.3% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 91.2% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 88.7% | Coming soon | Coming soon |
| GPQA | Coming soon | 95.5% | Coming soon |
| GPQA-D | Coming soon | 95.5% | Coming soon |

## FAQ

### Which is better overall, Muse Spark 1.1 or Sakana Fugu?

Sakana Fugu is ahead overall on BenchLM right now.

### Where is the biggest gap between Muse Spark 1.1 and Sakana Fugu?

The widest category gap is in multimodal & grounded, where the averages are 78.3 for Muse Spark 1.1 and 69.6 for Sakana Fugu.

### How many benchmarks does Muse Spark 1.1 cover on BenchLM?

Muse Spark 1.1 currently has 26 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

- [Muse Spark 1.1 vs Muse Spark 1.2](/compare/muse-spark-1-1-vs-muse-spark-1-2)
- [Sakana Fugu vs Muse Spark 1.2](/compare/muse-spark-1-2-vs-sakana-fugu)
- [Muse Spark 1.1 vs Muse Spark](/compare/muse-spark-vs-muse-spark-1-1)
- [Sakana Fugu vs Muse Spark](/compare/muse-spark-vs-sakana-fugu)

## Explore More

- [Muse Spark 1.1 profile](/models/muse-spark-1-1)
- [Sakana Fugu profile](/models/sakana-fugu)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
