Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Granite-4.0-H-1B
~43
0/8 categoriesGrok Code Fast 1
56
Winner · 3/8 categoriesGranite-4.0-H-1B· Grok Code Fast 1
Pick Grok Code Fast 1 if you want the stronger benchmark profile. Granite-4.0-H-1B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Grok Code Fast 1 is clearly ahead on the aggregate, 56 to 43. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok Code Fast 1's sharpest advantage is in multilingual, where it averages 73.7 against 37.8. The single biggest benchmark swing on the page is MGSM, 37.8% to 75%.
Grok Code Fast 1 gives you the larger context window at 256K, compared with 128K for Granite-4.0-H-1B.
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-1B | Grok Code Fast 1 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 59% |
| BrowseComp | — | 57% |
| OSWorld-Verified | — | 51% |
| Coding | ||
| HumanEval | 74% | 60% |
| SWE-bench Verified | — | 70.8% |
| LiveCodeBench | — | 80% |
| SWE-bench Pro | — | 42% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 40% |
| OfficeQA Pro | — | 63% |
| Reasoning | ||
| BBH | 60.4% | 75% |
| MuSR | — | 59% |
| LongBench v2 | — | 64% |
| MRCRv2 | — | 66% |
| KnowledgeGrok Code Fast 1 wins | ||
| MMLU | 59.4% | 64% |
| GPQA | 29.9% | 63% |
| MMLU-Pro | 34.0% | 65% |
| SuperGPQA | — | 61% |
| HLE | — | 7% |
| FrontierScience | — | 57% |
| SimpleQA | — | 61% |
| Instruction FollowingGrok Code Fast 1 wins | ||
| IFEval | 77.4% | 79% |
| MultilingualGrok Code Fast 1 wins | ||
| MGSM | 37.8% | 75% |
| MMLU-ProX | — | 73% |
| Mathematics | ||
| AIME 2023 | — | 64% |
| AIME 2024 | — | 66% |
| AIME 2025 | — | 65% |
| HMMT Feb 2023 | — | 60% |
| HMMT Feb 2024 | — | 62% |
| HMMT Feb 2025 | — | 61% |
| BRUMO 2025 | — | 63% |
| MATH-500 | — | 73% |
Grok Code Fast 1 is ahead overall, 56 to 43. The biggest single separator in this matchup is MGSM, where the scores are 37.8% and 75%.
Grok Code Fast 1 has the edge for knowledge tasks in this comparison, averaging 49 versus 32.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for instruction following in this comparison, averaging 79 versus 77.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Grok Code Fast 1 has the edge for multilingual tasks in this comparison, averaging 73.7 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.