Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek-R1
45
Winner · 3/8 categoriesGranite-4.0-H-1B
~43
0/8 categoriesDeepSeek-R1· Granite-4.0-H-1B
Pick DeepSeek-R1 if you want the stronger benchmark profile. Granite-4.0-H-1B only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.
DeepSeek-R1 has the cleaner overall profile here, landing at 45 versus 43. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
DeepSeek-R1's sharpest advantage is in multilingual, where it averages 60.4 against 37.8. The single biggest benchmark swing on the page is MMLU-Pro, 84% to 34.0%.
DeepSeek-R1 is also the more expensive model on tokens at $0.55 input / $2.19 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Granite-4.0-H-1B. That is roughly Infinityx on output cost alone. DeepSeek-R1 is the reasoning model in the pair, while Granite-4.0-H-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.
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 | DeepSeek-R1 | Granite-4.0-H-1B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | 42% | — |
| BrowseComp | 49% | — |
| OSWorld-Verified | 44% | — |
| Coding | ||
| HumanEval | 92% | 74% |
| SWE-bench Verified | 49.2% | — |
| LiveCodeBench | 19% | — |
| SWE-bench Pro | 25% | — |
| Multimodal & Grounded | ||
| MMMU-Pro | 43% | — |
| OfficeQA Pro | 53% | — |
| Reasoning | ||
| MuSR | 40% | — |
| BBH | 66% | 60.4% |
| LongBench v2 | 58% | — |
| MRCRv2 | 57% | — |
| ARC-AGI-2 | 1.3% | — |
| KnowledgeDeepSeek-R1 wins | ||
| MMLU | 90.8% | 59.4% |
| GPQA | 71.5% | 29.9% |
| SuperGPQA | 41% | — |
| MMLU-Pro | 84% | 34.0% |
| HLE | 14% | — |
| FrontierScience | 44% | — |
| SimpleQA | 30.1% | — |
| Instruction FollowingDeepSeek-R1 wins | ||
| IFEval | 83.3% | 77.4% |
| MultilingualDeepSeek-R1 wins | ||
| MGSM | 61% | 37.8% |
| MMLU-ProX | 60% | — |
| Mathematics | ||
| AIME 2023 | 44% | — |
| AIME 2024 | 79.8% | — |
| AIME 2025 | 45% | — |
| HMMT Feb 2023 | 40% | — |
| HMMT Feb 2024 | 42% | — |
| HMMT Feb 2025 | 41% | — |
| BRUMO 2025 | 43% | — |
| MATH-500 | 97.3% | — |
DeepSeek-R1 is ahead overall, 45 to 43. The biggest single separator in this matchup is MMLU-Pro, where the scores are 84% and 34.0%.
DeepSeek-R1 has the edge for knowledge tasks in this comparison, averaging 47 versus 32.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for instruction following in this comparison, averaging 83.3 versus 77.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
DeepSeek-R1 has the edge for multilingual tasks in this comparison, averaging 60.4 versus 37.8. 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.