# Granite-4.0-H-350M vs Granite 4.2 8B

> Side-by-side benchmark comparison for Granite-4.0-H-350M and Granite 4.2 8B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/granite-4-0-h-350m-vs-granite-4-2-8b
- Last updated: October 15, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Granite-4.0-H-350M and Granite 4.2 8B share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Granite 4.2 8B has the larger published context window at 128K.

## Model Snapshot

| Property | Granite-4.0-H-350M | Granite 4.2 8B |
|----------|----------|----------|
| Creator | IBM | IBM |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 32K | 128K |
| Independent public score (not head-to-head) | 28.48 | 33.4 |
| Benchmarks Covered | 7 | 14 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: Coming soon
- Granite 4.2 8B public-lane score: 15.7 (Estimated · #113/127)

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | Coming soon | 20.6% | Coming soon |
| τ³-bench results | Coming soon | 58.1% | Coming soon |
| BFCL v4 | Coming soon | 52.4% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: Coming soon
- Granite 4.2 8B public-lane score: 17.2 (Estimated · #125/150)

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| HumanEval | 38% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 47.7% | Coming soon |
| SWE-bench Pro | Coming soon | 19.1% | Coming soon |
| SWE Multilingual | Coming soon | 30.8% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 20.6% | Coming soon |
| LiveCodeBench v6 | Coming soon | 73.2% | Coming soon |
| SciCode | Coming soon | 36.1% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: 25.9 (Unranked · 3 rankable rows)
- Granite 4.2 8B public-lane score: 56.8 (Unranked · 2 rankable rows)

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| BBH | 33.3% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: 17.1 (Supported · #181/184)
- Granite 4.2 8B public-lane score: 30.6 (Supported · #154/184)

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| MMLU | 36.2% | Coming soon | Coming soon |
| GPQA | 26.1% | 64.1% | Granite 4.2 8B |
| MMLU-Pro | 14.4% | 74.0% | Granite 4.2 8B |

### Multilingual

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: Coming soon
- Granite 4.2 8B public-lane score: Coming soon

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| MGSM | 16.2% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: 28.8 (#136/146)
- Granite 4.2 8B public-lane score: 86.5 (#41/146)

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 61.6% | Coming soon | Coming soon |
| IFBench | Coming soon | 79.3% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Granite-4.0-H-350M public-lane score: Coming soon
- Granite 4.2 8B public-lane score: Coming soon

| Benchmark | Granite-4.0-H-350M | Granite 4.2 8B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | Coming soon | 86.7% | Coming soon |
| HMMT Feb 2025 | Coming soon | 78.3% | Coming soon |

## FAQ

### Is there enough evidence to pick between Granite-4.0-H-350M and Granite 4.2 8B?

Not yet. The models share only 2 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-4.0-H-350M vs Granite-4.0-350M](/compare/granite-4-0-350m-vs-granite-4-0-h-350m)
- [Granite 4.2 8B vs Granite-4.0-350M](/compare/granite-4-0-350m-vs-granite-4-2-8b)
- [Granite-4.0-H-350M vs Granite 4.2 30B](/compare/granite-4-0-h-350m-vs-granite-4-2-30b)
- [Granite 4.2 8B vs Granite 4.2 30B](/compare/granite-4-2-30b-vs-granite-4-2-8b)

## Explore More

- [Granite-4.0-H-350M profile](/models/granite-4-0-h-350m)
- [Granite 4.2 8B profile](/models/granite-4-2-8b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)