Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 8B
~50
1/8 categoriesGemini 1.5 Pro
50
3/8 categories1-bit Bonsai 8B· Gemini 1.5 Pro
Treat this as a split decision. 1-bit Bonsai 8B makes more sense if instruction following is the priority; Gemini 1.5 Pro is the better fit if reasoning is the priority or you need the larger 2M context window.
1-bit Bonsai 8B and Gemini 1.5 Pro 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.
Gemini 1.5 Pro gives you the larger context window at 2M, compared with 64K for 1-bit Bonsai 8B.
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 8B | Gemini 1.5 Pro |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 45% |
| BrowseComp | — | 64% |
| OSWorld-Verified | — | 45% |
| Coding | ||
| HumanEval | — | 56% |
| SWE-bench Verified | — | 5% |
| LiveCodeBench | — | 22% |
| SWE-bench Pro | — | 18% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 75% |
| OfficeQA Pro | — | 73% |
| ReasoningGemini 1.5 Pro wins | ||
| MuSR | 50% | 60% |
| BBH | — | 74% |
| LongBench v2 | — | 70% |
| MRCRv2 | — | 73% |
| KnowledgeGemini 1.5 Pro wins | ||
| GPQA | 30% | 56.8% |
| MMLU | — | 64% |
| SuperGPQA | — | 62% |
| MMLU-Pro | — | 57% |
| HLE | — | 1% |
| FrontierScience | — | 54% |
| SimpleQA | — | 62% |
| Instruction Following1-bit Bonsai 8B wins | ||
| IFEval | 79.8% | 77% |
| Multilingual | ||
| MGSM | — | 76% |
| MMLU-ProX | — | 66% |
| MathematicsGemini 1.5 Pro wins | ||
| MATH-500 | 66% | 73% |
| AIME 2023 | — | 64% |
| AIME 2024 | — | 66% |
| AIME 2025 | — | 65% |
| HMMT Feb 2023 | — | 60% |
| HMMT Feb 2024 | — | 62% |
| HMMT Feb 2025 | — | 61% |
| BRUMO 2025 | — | 63% |
1-bit Bonsai 8B and Gemini 1.5 Pro are tied on overall score, so the right pick depends on which category matters most for your use case.
Gemini 1.5 Pro has the edge for knowledge tasks in this comparison, averaging 44.8 versus 30. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Gemini 1.5 Pro has the edge for math in this comparison, averaging 66.3 versus 66. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Gemini 1.5 Pro has the edge for reasoning in this comparison, averaging 68.3 versus 50. Inside this category, MuSR is the benchmark that creates the most daylight between them.
1-bit Bonsai 8B has the edge for instruction following in this comparison, averaging 79.8 versus 77. 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.