Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 8B
~50
Winner · 2/8 categoriesGemini 2.5 Flash
49
2/8 categories1-bit Bonsai 8B· Gemini 2.5 Flash
Pick 1-bit Bonsai 8B if you want the stronger benchmark profile. Gemini 2.5 Flash only becomes the better choice if reasoning is the priority or you need the larger 1M context window.
1-bit Bonsai 8B finishes one point ahead overall, 50 to 49. 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 8B's sharpest advantage is in mathematics, where it averages 66 against 55.6. The single biggest benchmark swing on the page is GPQA, 30% to 49%. Gemini 2.5 Flash does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
Gemini 2.5 Flash is also the more expensive model on tokens at $0.15 input / $0.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for 1-bit Bonsai 8B. That is roughly Infinityx on output cost alone. Gemini 2.5 Flash gives you the larger context window at 1M, 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 2.5 Flash |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 44% |
| BrowseComp | — | 58% |
| OSWorld-Verified | — | 41% |
| Coding | ||
| HumanEval | — | 42% |
| SWE-bench Verified | — | 23% |
| LiveCodeBench | — | 18% |
| SWE-bench Pro | — | 25% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 69% |
| OfficeQA Pro | — | 66% |
| ReasoningGemini 2.5 Flash wins | ||
| MuSR | 50% | 46% |
| BBH | — | 75% |
| LongBench v2 | — | 68% |
| MRCRv2 | — | 68% |
| KnowledgeGemini 2.5 Flash wins | ||
| GPQA | 30% | 49% |
| MMLU | — | 50% |
| SuperGPQA | — | 47% |
| MMLU-Pro | — | 64% |
| HLE | — | 1% |
| FrontierScience | — | 49% |
| SimpleQA | — | 48% |
| Instruction Following1-bit Bonsai 8B wins | ||
| IFEval | 79.8% | 79% |
| Multilingual | ||
| MGSM | — | 74% |
| MMLU-ProX | — | 69% |
| Mathematics1-bit Bonsai 8B wins | ||
| MATH-500 | 66% | 72% |
| AIME 2023 | — | 50% |
| AIME 2024 | — | 52% |
| AIME 2025 | — | 51% |
| HMMT Feb 2023 | — | 46% |
| HMMT Feb 2024 | — | 48% |
| HMMT Feb 2025 | — | 47% |
| BRUMO 2025 | — | 49% |
1-bit Bonsai 8B is ahead overall, 50 to 49. The biggest single separator in this matchup is GPQA, where the scores are 30% and 49%.
Gemini 2.5 Flash has the edge for knowledge tasks in this comparison, averaging 40.9 versus 30. Inside this category, GPQA is the benchmark that creates the most daylight between them.
1-bit Bonsai 8B has the edge for math in this comparison, averaging 66 versus 55.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Gemini 2.5 Flash has the edge for reasoning in this comparison, averaging 62.1 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 79. 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.