Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Granite-4.0-H-1B
~43
0/8 categoriesMistral 8x7B
44
Winner · 3/8 categoriesGranite-4.0-H-1B· Mistral 8x7B
Pick Mistral 8x7B if you want the stronger benchmark profile. Granite-4.0-H-1B only becomes the better choice if you need the larger 128K context window.
Mistral 8x7B finishes one point ahead overall, 44 to 43. 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.
Mistral 8x7B's sharpest advantage is in multilingual, where it averages 72.1 against 37.8. The single biggest benchmark swing on the page is HumanEval, 74% to 32.3%.
Granite-4.0-H-1B gives you the larger context window at 128K, compared with 32K for Mistral 8x7B.
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 | Mistral 8x7B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 40% |
| BrowseComp | — | 47% |
| OSWorld-Verified | — | 38% |
| Coding | ||
| HumanEval | 74% | 32.3% |
| SWE-bench Verified | — | 28% |
| LiveCodeBench | — | 23% |
| SWE-bench Pro | — | 28% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 42% |
| OfficeQA Pro | — | 56% |
| Reasoning | ||
| BBH | 60.4% | 67.1% |
| MuSR | — | 61% |
| LongBench v2 | — | 57% |
| MRCRv2 | — | 53% |
| KnowledgeMistral 8x7B wins | ||
| MMLU | 59.4% | 71.3% |
| GPQA | 29.9% | 64% |
| MMLU-Pro | 34.0% | 65% |
| SuperGPQA | — | 62% |
| HLE | — | 8% |
| FrontierScience | — | 56% |
| SimpleQA | — | 63% |
| Instruction FollowingMistral 8x7B wins | ||
| IFEval | 77.4% | 78% |
| MultilingualMistral 8x7B wins | ||
| MGSM | 37.8% | 74% |
| MMLU-ProX | — | 71% |
| 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 | — | 73% |
Mistral 8x7B is ahead overall, 44 to 43. The biggest single separator in this matchup is HumanEval, where the scores are 74% and 32.3%.
Mistral 8x7B has the edge for knowledge tasks in this comparison, averaging 49.5 versus 32.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Mistral 8x7B has the edge for instruction following in this comparison, averaging 78 versus 77.4. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Mistral 8x7B has the edge for multilingual tasks in this comparison, averaging 72.1 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.