Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Granite-4.0-1B
~40
1/8 categoriesNemotron Ultra 253B
41
Winner · 2/8 categoriesGranite-4.0-1B· Nemotron Ultra 253B
Pick Nemotron Ultra 253B if you want the stronger benchmark profile. Granite-4.0-1B only becomes the better choice if instruction following is the priority or you need the larger 128K context window.
Nemotron Ultra 253B finishes one point ahead overall, 41 to 40. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Nemotron Ultra 253B's sharpest advantage is in multilingual, where it averages 70.1 against 27.5. The single biggest benchmark swing on the page is MGSM, 27.5% to 74%. 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.
Nemotron Ultra 253B is the reasoning model in the pair, while Granite-4.0-1B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Granite-4.0-1B gives you the larger context window at 128K, compared with 32K for Nemotron Ultra 253B.
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 | Nemotron Ultra 253B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 46% |
| BrowseComp | — | 50% |
| OSWorld-Verified | — | 45% |
| Coding | ||
| HumanEval | 73% | 41% |
| SWE-bench Verified | — | 31% |
| LiveCodeBench | — | 30% |
| SWE-bench Pro | — | 38% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 37% |
| OfficeQA Pro | — | 54% |
| Reasoning | ||
| BBH | 59.7% | 77% |
| MuSR | — | 45% |
| LongBench v2 | — | 55% |
| MRCRv2 | — | 56% |
| KnowledgeNemotron Ultra 253B wins | ||
| MMLU | 59.7% | 49% |
| GPQA | 29.7% | 48% |
| MMLU-Pro | 32.9% | 63% |
| SuperGPQA | — | 46% |
| HLE | — | 11% |
| FrontierScience | — | 49% |
| SimpleQA | — | 47% |
| Instruction FollowingGranite-4.0-1B wins | ||
| IFEval | 78.5% | 78% |
| MultilingualNemotron Ultra 253B wins | ||
| MGSM | 27.5% | 74% |
| MMLU-ProX | — | 68% |
| Mathematics | ||
| AIME 2023 | — | 49% |
| AIME 2024 | — | 51% |
| AIME 2025 | — | 50% |
| HMMT Feb 2023 | — | 45% |
| HMMT Feb 2024 | — | 47% |
| HMMT Feb 2025 | — | 46% |
| BRUMO 2025 | — | 48% |
| MATH-500 | — | 74% |
Nemotron Ultra 253B is ahead overall, 41 to 40. The biggest single separator in this matchup is MGSM, where the scores are 27.5% and 74%.
Nemotron Ultra 253B has the edge for knowledge tasks in this comparison, averaging 42.6 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 78. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Nemotron Ultra 253B has the edge for multilingual tasks in this comparison, averaging 70.1 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.