Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Sibling matchup inside the Granite 4.0 1B family.
Granite-4.0-1B
~40
1/8 categoriesGranite-4.0-H-1B
~43
Winner · 2/8 categoriesGranite-4.0-1B· Granite-4.0-H-1B
Granite-4.0-1B makes more sense if instruction following is the priority, while Granite-4.0-H-1B is the cleaner fit if multilingual is the priority.
Granite-4.0-1B and Granite-4.0-H-1B sit in the same Granite 4.0 1B family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
Granite-4.0-H-1B has the cleaner overall profile here, landing at 43 versus 40. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Granite-4.0-H-1B's sharpest advantage is in multilingual, where it averages 37.8 against 27.5. The single biggest benchmark swing on the page is MGSM, 27.5% to 37.8%. Granite-4.0-1B does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Granite-4.0-1B | Granite-4.0-H-1B |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| Coding | ||
| HumanEval | 73% | 74% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| BBH | 59.7% | 60.4% |
| KnowledgeGranite-4.0-H-1B wins | ||
| MMLU | 59.7% | 59.4% |
| GPQA | 29.7% | 29.9% |
| MMLU-Pro | 32.9% | 34.0% |
| Instruction FollowingGranite-4.0-1B wins | ||
| IFEval | 78.5% | 77.4% |
| MultilingualGranite-4.0-H-1B wins | ||
| MGSM | 27.5% | 37.8% |
| Mathematics | ||
| Coming soon | ||
Granite-4.0-1B and Granite-4.0-H-1B are sibling variants in the Granite 4.0 1B family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. Granite-4.0-H-1B is ahead overall 43 to 40.
Granite-4.0-H-1B has the edge for knowledge tasks in this comparison, averaging 32.6 versus 31.7. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Granite-4.0-1B has the edge for instruction following in this comparison, averaging 78.5 versus 77.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Granite-4.0-H-1B has the edge for multilingual tasks in this comparison, averaging 37.8 versus 27.5. Inside this category, MGSM is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.