# Inkling vs Fugu Cyber

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

- Canonical page: https://benchlm.ai/compare/inkling-vs-sakana-fugu-cyber
- Last updated: September 4, 2026

- Shared sourced benchmarks: 0
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

No benchmark verdict yet: there is no shared sourced benchmark row for Inkling and Fugu Cyber.

## Summary

- Inkling and Fugu Cyber do not currently share a sourced benchmark row. The mirror therefore compares metadata, pricing, context windows, and each model's separately reported coverage without naming a benchmark winner.

## Model Snapshot

| Property | Inkling | Fugu Cyber |
|----------|----------|----------|
| Creator | Thinking Machines Lab | Sakana AI |
| Type | Open Weight | Proprietary |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 1M |
| Independent public score (not head-to-head) | 62.78 | null |
| Benchmarks Covered | 21 | 2 |
| Pricing (input/output) | $1.87 / $4.68 | $6.00 / $36.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Inkling public-lane score: 40.7 (Supported · #119/151)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 63.8% | Coming soon | Coming soon |
| BrowseComp | 77.1% | Coming soon | Coming soon |
| MCP Atlas | 74.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 47.6% | Coming soon | Coming soon |
| CyberGym | Coming soon | 86.9% | Coming soon |
| CTI-REALM | Coming soon | 72.1% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Inkling public-lane score: 41.4 (Supported · #132/183)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.6% | Coming soon | Coming soon |
| SWE-bench Pro | 54.3% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 63.8% | Coming soon | Coming soon |
| FrontierSWE v2 | 4.1% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 85.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 77.6% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Inkling public-lane score: 48.7 (#38/48)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 73.5% | Coming soon | Coming soon |
| CharXiv | 82% | Coming soon | Coming soon |
| CharXiv w/o tools | 78.1% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Inkling public-lane score: 73.7 (Unranked · 2 rankable rows)
- Fugu Cyber public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- Inkling public-lane score: 58.5 (Supported · #45/181)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.9% | Coming soon | Coming soon |
| GPQA-D | 87.9% | Coming soon | Coming soon |
| HLE | 46% | Coming soon | Coming soon |
| HLE w/o tools | 30% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 87.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.3% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Inkling public-lane score: 85.2 (#43/120)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 79.8% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Inkling public-lane score: 78.9 (Unranked · 1 rankable row)
- Fugu Cyber public-lane score: Coming soon

| Benchmark | Inkling | Fugu Cyber | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 97.1% | Coming soon | Coming soon |

## FAQ

### Can I compare Inkling and Fugu Cyber on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but sourced benchmark coverage is still incomplete for a fair score-level comparison.

### Why does this page show "coming soon" values?

BenchLM only calls winners when public benchmark coverage is available on both sides of the comparison.

## Related Comparisons

- [Inkling vs Inkling-Small](/compare/inkling-vs-inkling-small)
- [Fugu Cyber vs Inkling-Small](/compare/inkling-small-vs-sakana-fugu-cyber)
- [Inkling vs Sakana Fugu-Ultra](/compare/inkling-vs-sakana-fugu-ultra)
- [Fugu Cyber vs Sakana Fugu-Ultra](/compare/sakana-fugu-cyber-vs-sakana-fugu-ultra)

## Explore More

- [Inkling profile](/models/inkling)
- [Fugu Cyber profile](/models/sakana-fugu-cyber)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)