Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 1.7B
~39
0/8 categoriesLFM2.5-350M
~39
2/8 categories1-bit Bonsai 1.7B· LFM2.5-350M
Treat this as a split decision. 1-bit Bonsai 1.7B makes more sense if its workflow fits your team better; LFM2.5-350M is the better fit if instruction following is the priority.
1-bit Bonsai 1.7B and LFM2.5-350M finish on the same overall score, so this is less about a single winner and more about where the edge shows up. The headline says tie; the benchmark table is where the real choice happens.
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 | LFM2.5-350M |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| Coding | ||
| Coming soon | ||
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| MuSR | 45.1% | — |
| KnowledgeLFM2.5-350M wins | ||
| GPQA | 20.7% | 30.6% |
| MMLU-Pro | — | 20.0% |
| Instruction FollowingLFM2.5-350M wins | ||
| IFEval | 63% | 77.0% |
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| MATH-500 | 34.4% | — |
1-bit Bonsai 1.7B and LFM2.5-350M are tied on overall score, so the right pick depends on which category matters most for your use case.
LFM2.5-350M has the edge for knowledge tasks in this comparison, averaging 23.8 versus 20.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
LFM2.5-350M has the edge for instruction following in this comparison, averaging 77 versus 63. 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.