Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 1.7B
~39
Winner · 2/8 categoriesGranite-4.0-350M
~27
0/8 categories1-bit Bonsai 1.7B· Granite-4.0-350M
Pick 1-bit Bonsai 1.7B if you want the stronger benchmark profile. Granite-4.0-350M only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
1-bit Bonsai 1.7B is clearly ahead on the aggregate, 39 to 27. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
1-bit Bonsai 1.7B's sharpest advantage is in knowledge, where it averages 20.7 against 18.5. The single biggest benchmark swing on the page is GPQA, 20.7% to 26.1%.
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 | 1-bit Bonsai 1.7B | Granite-4.0-350M |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| Coding | ||
| HumanEval | — | 38% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| MuSR | 45.1% | — |
| BBH | — | 33.3% |
| Knowledge1-bit Bonsai 1.7B wins | ||
| GPQA | 20.7% | 26.1% |
| MMLU | — | 36.2% |
| MMLU-Pro | — | 14.4% |
| Instruction Following1-bit Bonsai 1.7B wins | ||
| IFEval | 63% | 61.6% |
| Multilingual | ||
| MGSM | — | 16.2% |
| Mathematics | ||
| MATH-500 | 34.4% | — |
1-bit Bonsai 1.7B is ahead overall, 39 to 27. The biggest single separator in this matchup is GPQA, where the scores are 20.7% and 26.1%.
1-bit Bonsai 1.7B has the edge for knowledge tasks in this comparison, averaging 20.7 versus 18.5. Inside this category, GPQA is the benchmark that creates the most daylight between them.
1-bit Bonsai 1.7B has the edge for instruction following in this comparison, averaging 63 versus 61.6. Inside this category, IFEval 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.