Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Granite-4.0-H-350M
~24
0/8 categoriesNemotron 3 Super 100B
57
Winner · 3/8 categoriesGranite-4.0-H-350M· Nemotron 3 Super 100B
Pick Nemotron 3 Super 100B 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.
Nemotron 3 Super 100B is clearly ahead on the aggregate, 57 to 24. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Nemotron 3 Super 100B's sharpest advantage is in multilingual, where it averages 79.5 against 14.7. The single biggest benchmark swing on the page is MGSM, 14.7% to 84%.
Nemotron 3 Super 100B gives you the larger context window at 1M, compared with 32K for Granite-4.0-H-350M.
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-H-350M | Nemotron 3 Super 100B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 56% |
| BrowseComp | — | 61% |
| OSWorld-Verified | — | 54% |
| Coding | ||
| HumanEval | 39% | 57% |
| SWE-bench Verified | — | 44% |
| LiveCodeBench | — | 38% |
| SWE-bench Pro | — | 44% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 55% |
| OfficeQA Pro | — | 67% |
| Reasoning | ||
| BBH | 33.1% | 83% |
| MuSR | — | 60% |
| LongBench v2 | — | 75% |
| MRCRv2 | — | 75% |
| KnowledgeNemotron 3 Super 100B wins | ||
| MMLU | 35.0% | 65% |
| GPQA | 24.1% | 64% |
| MMLU-Pro | 12.1% | 72% |
| SuperGPQA | — | 62% |
| HLE | — | 13% |
| FrontierScience | — | 63% |
| SimpleQA | — | 62% |
| Instruction FollowingNemotron 3 Super 100B wins | ||
| IFEval | 55.4% | 84% |
| MultilingualNemotron 3 Super 100B wins | ||
| MGSM | 14.7% | 84% |
| MMLU-ProX | — | 77% |
| Mathematics | ||
| AIME 2023 | — | 65% |
| AIME 2024 | — | 67% |
| AIME 2025 | — | 66% |
| HMMT Feb 2023 | — | 61% |
| HMMT Feb 2024 | — | 63% |
| HMMT Feb 2025 | — | 62% |
| BRUMO 2025 | — | 64% |
| MATH-500 | — | 83% |
Nemotron 3 Super 100B is ahead overall, 57 to 24. The biggest single separator in this matchup is MGSM, where the scores are 14.7% and 84%.
Nemotron 3 Super 100B has the edge for knowledge tasks in this comparison, averaging 53.4 versus 16.4. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Nemotron 3 Super 100B has the edge for instruction following in this comparison, averaging 84 versus 55.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Nemotron 3 Super 100B has the edge for multilingual tasks in this comparison, averaging 79.5 versus 14.7. 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.