Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 4B
~44
Winner · 1/8 categoriesPhi-4
40
2/8 categories1-bit Bonsai 4B· Phi-4
Pick 1-bit Bonsai 4B if you want the stronger benchmark profile. Phi-4 only becomes the better choice if mathematics is the priority.
1-bit Bonsai 4B is clearly ahead on the aggregate, 44 to 40. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
1-bit Bonsai 4B's sharpest advantage is in reasoning, where it averages 41.4 against 31.4. The single biggest benchmark swing on the page is MATH-500, 65.8% to 94.6%. Phi-4 does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
1-bit Bonsai 4B gives you the larger context window at 32K, compared with 16K for Phi-4.
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 4B | Phi-4 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 44% |
| BrowseComp | — | 35% |
| OSWorld-Verified | — | 34% |
| Coding | ||
| HumanEval | — | 82.6% |
| SWE-bench Pro | — | 55% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 54% |
| OfficeQA Pro | — | 38% |
| Reasoning1-bit Bonsai 4B wins | ||
| MuSR | 41.4% | — |
| LongBench v2 | — | 30% |
| MRCRv2 | — | 33% |
| KnowledgePhi-4 wins | ||
| GPQA | 28.7% | 56.1% |
| MMLU | — | 84.8% |
| FrontierScience | — | 52% |
| Instruction Following | ||
| IFEval | 69.6% | — |
| Multilingual | ||
| MGSM | — | 80.6% |
| MMLU-ProX | — | 60% |
| MathematicsPhi-4 wins | ||
| MATH-500 | 65.8% | 94.6% |
1-bit Bonsai 4B is ahead overall, 44 to 40. The biggest single separator in this matchup is MATH-500, where the scores are 65.8% and 94.6%.
Phi-4 has the edge for knowledge tasks in this comparison, averaging 53.6 versus 28.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Phi-4 has the edge for math in this comparison, averaging 94.6 versus 65.8. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
1-bit Bonsai 4B has the edge for reasoning in this comparison, averaging 41.4 versus 31.4. Phi-4 stays close enough that the answer can still flip depending on your workload.
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.