Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DBRX Instruct
41
Winner · 2/8 categoriesGranite-4.0-H-350M
~24
0/8 categoriesDBRX Instruct· Granite-4.0-H-350M
Pick DBRX Instruct if you want the stronger benchmark profile. Granite-4.0-H-350M only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
DBRX Instruct is clearly ahead on the aggregate, 41 to 24. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DBRX Instruct's sharpest advantage is in knowledge, where it averages 52 against 16.4. The single biggest benchmark swing on the page is MMLU, 73.7% to 35.0%.
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 | DBRX Instruct | Granite-4.0-H-350M |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 41% | — |
| BrowseComp | 31% | — |
| OSWorld-Verified | 29% | — |
| Coding | ||
| HumanEval | 70.1% | 39% |
| SWE-bench Pro | 48% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 36% | — |
| OfficeQA Pro | 35% | — |
| Reasoning | ||
| LongBench v2 | 36% | — |
| MRCRv2 | 37% | — |
| BBH | — | 33.1% |
| KnowledgeDBRX Instruct wins | ||
| MMLU | 73.7% | 35.0% |
| FrontierScience | 52% | — |
| GPQA | — | 24.1% |
| MMLU-Pro | — | 12.1% |
| Instruction Following | ||
| IFEval | — | 55.4% |
| MultilingualDBRX Instruct wins | ||
| MMLU-ProX | 46% | — |
| MGSM | — | 14.7% |
| Mathematics | ||
| Coming soon | ||
DBRX Instruct is ahead overall, 41 to 24. The biggest single separator in this matchup is MMLU, where the scores are 73.7% and 35.0%.
DBRX Instruct has the edge for knowledge tasks in this comparison, averaging 52 versus 16.4. Inside this category, MMLU is the benchmark that creates the most daylight between them.
DBRX Instruct has the edge for multilingual tasks in this comparison, averaging 46 versus 14.7. Granite-4.0-H-350M stays close enough that the answer can still flip depending on your workload.
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.