Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 4B
~44
Winner · 1/8 categoriesMoonshot v1
43
3/8 categories1-bit Bonsai 4B· Moonshot v1
Pick 1-bit Bonsai 4B if you want the stronger benchmark profile. Moonshot v1 only becomes the better choice if knowledge is the priority or you need the larger 128K context window.
1-bit Bonsai 4B 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.
1-bit Bonsai 4B's sharpest advantage is in mathematics, where it averages 65.8 against 53.1. The single biggest benchmark swing on the page is GPQA, 28.7% to 52%. Moonshot v1 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Moonshot v1 gives you the larger context window at 128K, compared with 32K for 1-bit Bonsai 4B.
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 | Moonshot v1 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 39% |
| BrowseComp | — | 49% |
| Coding | ||
| HumanEval | — | 45% |
| SWE-bench Verified | — | 34% |
| LiveCodeBench | — | 21% |
| SWE-bench Pro | — | 30% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 49% |
| OfficeQA Pro | — | 57% |
| ReasoningMoonshot v1 wins | ||
| MuSR | 41.4% | 49% |
| BBH | — | 73% |
| LongBench v2 | — | 58% |
| MRCRv2 | — | 56% |
| KnowledgeMoonshot v1 wins | ||
| GPQA | 28.7% | 52% |
| MMLU | — | 53% |
| SuperGPQA | — | 50% |
| MMLU-Pro | — | 64% |
| HLE | — | 5% |
| FrontierScience | — | 49% |
| SimpleQA | — | 51% |
| Instruction FollowingMoonshot v1 wins | ||
| IFEval | 69.6% | 77% |
| Multilingual | ||
| MGSM | — | 73% |
| MMLU-ProX | — | 68% |
| Mathematics1-bit Bonsai 4B wins | ||
| MATH-500 | 65.8% | — |
| AIME 2023 | — | 53% |
| AIME 2024 | — | 55% |
| AIME 2025 | — | 54% |
| HMMT Feb 2023 | — | 49% |
| HMMT Feb 2024 | — | 51% |
| HMMT Feb 2025 | — | 50% |
| BRUMO 2025 | — | 52% |
1-bit Bonsai 4B is ahead overall, 44 to 43. The biggest single separator in this matchup is GPQA, where the scores are 28.7% and 52%.
Moonshot v1 has the edge for knowledge tasks in this comparison, averaging 42.9 versus 28.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
1-bit Bonsai 4B has the edge for math in this comparison, averaging 65.8 versus 53.1. Moonshot v1 stays close enough that the answer can still flip depending on your workload.
Moonshot v1 has the edge for reasoning in this comparison, averaging 54.9 versus 41.4. Inside this category, MuSR is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for instruction following in this comparison, averaging 77 versus 69.6. 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.