# Granite 4.2 3B vs Sakana Fugu-Ultra

> Side-by-side benchmark comparison for Granite 4.2 3B and Sakana Fugu-Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/granite-4-2-3b-vs-sakana-fugu-ultra
- Last updated: September 10, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Granite 4.2 3B and Sakana Fugu-Ultra share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Sakana Fugu-Ultra has the lower published output-token price.
- Sakana Fugu-Ultra has the larger published context window at 1M.

## Model Snapshot

| Property | Granite 4.2 3B | Sakana Fugu-Ultra |
|----------|----------|----------|
| Creator | IBM | Sakana AI |
| Type | Open Weight | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 1M |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 9 | 11 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| τ³-bench results | 45.8% | Coming soon | Coming soon |
| BFCL v4 | 52.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 82.1% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 69.7% | 93.2% | Sakana Fugu-Ultra |
| SciCode | 24.1% | 58.7% | Sakana Fugu-Ultra |
| SWE-bench Pro | Coming soon | 73.7% | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 82.1% | Coming soon |
| LiveCodeBench Pro | Coming soon | 90.8% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: 72.8 (Unranked · 1 rankable row)

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | Coming soon | 86.6% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: 37.7 (Unranked · 2 rankable rows)
- Sakana Fugu-Ultra public-lane score: 77.9 (Unranked · 1 rankable row)

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | Coming soon | 93.6% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 54.8% | 95.5% | Sakana Fugu-Ultra |
| MMLU-Pro | 67.8% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 95.5% | Coming soon |
| HLE w/o tools | Coming soon | 50% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 74.3% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Granite 4.2 3B public-lane score: Coming soon
- Sakana Fugu-Ultra public-lane score: Coming soon

| Benchmark | Granite 4.2 3B | Sakana Fugu-Ultra | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 78.3% | Coming soon | Coming soon |
| HMMT Feb 2025 | 66.7% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Granite 4.2 3B and Sakana Fugu-Ultra?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Granite 4.2 3B vs Granite 4.2 8B](/compare/granite-4-2-3b-vs-granite-4-2-8b)
- [Sakana Fugu-Ultra vs Granite 4.2 8B](/compare/granite-4-2-8b-vs-sakana-fugu-ultra)
- [Granite 4.2 3B vs Granite 4.2 30B](/compare/granite-4-2-30b-vs-granite-4-2-3b)
- [Sakana Fugu-Ultra vs Granite 4.2 30B](/compare/granite-4-2-30b-vs-sakana-fugu-ultra)

## Explore More

- [Granite 4.2 3B profile](/models/granite-4-2-3b)
- [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)