Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 1.7B
~39
Winner · 1/8 categoriesGPT-OSS 20B
35
2/8 categories1-bit Bonsai 1.7B· GPT-OSS 20B
Pick 1-bit Bonsai 1.7B if you want the stronger benchmark profile. GPT-OSS 20B only becomes the better choice if knowledge is the priority or you need the larger 128K context window.
1-bit Bonsai 1.7B is clearly ahead on the aggregate, 39 to 35. 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 reasoning, where it averages 45.1 against 42.4. The single biggest benchmark swing on the page is MATH-500, 34.4% to 59%. GPT-OSS 20B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-OSS 20B gives you the larger context window at 128K, compared with 32K for 1-bit Bonsai 1.7B.
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 | GPT-OSS 20B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 35% |
| OSWorld-Verified | — | 31% |
| Coding | ||
| HumanEval | — | 23% |
| SWE-bench Verified | — | 14% |
| LiveCodeBench | — | 11% |
| SWE-bench Pro | — | 18% |
| React Native Evals | — | 64.3% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 31% |
| OfficeQA Pro | — | 42% |
| Reasoning1-bit Bonsai 1.7B wins | ||
| MuSR | 45.1% | 27% |
| LongBench v2 | — | 48% |
| MRCRv2 | — | 48% |
| KnowledgeGPT-OSS 20B wins | ||
| GPQA | 20.7% | 30% |
| MMLU | — | 85.3% |
| SuperGPQA | — | 28% |
| MMLU-Pro | — | 53% |
| HLE | — | 1% |
| FrontierScience | — | 34% |
| SimpleQA | — | 29% |
| Instruction Following | ||
| IFEval | 63% | — |
| Multilingual | ||
| MGSM | — | 61% |
| MMLU-ProX | — | 59% |
| MathematicsGPT-OSS 20B wins | ||
| MATH-500 | 34.4% | 59% |
| AIME 2023 | — | 31% |
| AIME 2024 | — | 33% |
| AIME 2025 | — | 32% |
| HMMT Feb 2023 | — | 27% |
| HMMT Feb 2024 | — | 29% |
| HMMT Feb 2025 | — | 28% |
| BRUMO 2025 | — | 30% |
1-bit Bonsai 1.7B is ahead overall, 39 to 35. The biggest single separator in this matchup is MATH-500, where the scores are 34.4% and 59%.
GPT-OSS 20B has the edge for knowledge tasks in this comparison, averaging 28.7 versus 20.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-OSS 20B has the edge for math in this comparison, averaging 38.1 versus 34.4. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
1-bit Bonsai 1.7B has the edge for reasoning in this comparison, averaging 45.1 versus 42.4. Inside this category, MuSR 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.