Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 4B
~44
0/8 categoriesQwen2.5-1M
62
Winner · 4/8 categories1-bit Bonsai 4B· Qwen2.5-1M
Pick Qwen2.5-1M if you want the stronger benchmark profile. 1-bit Bonsai 4B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Qwen2.5-1M is clearly ahead on the aggregate, 62 to 44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen2.5-1M's sharpest advantage is in reasoning, where it averages 80.9 against 41.4. The single biggest benchmark swing on the page is GPQA, 28.7% to 83%.
Qwen2.5-1M gives you the larger context window at 1M, 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 | Qwen2.5-1M |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 65% |
| BrowseComp | — | 72% |
| OSWorld-Verified | — | 59% |
| Coding | ||
| HumanEval | — | 76% |
| SWE-bench Verified | — | 47% |
| LiveCodeBench | — | 40% |
| SWE-bench Pro | — | 49% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 63% |
| OfficeQA Pro | — | 75% |
| ReasoningQwen2.5-1M wins | ||
| MuSR | 41.4% | 79% |
| BBH | — | 82% |
| LongBench v2 | — | 82% |
| MRCRv2 | — | 81% |
| KnowledgeQwen2.5-1M wins | ||
| GPQA | 28.7% | 83% |
| MMLU | — | 84% |
| SuperGPQA | — | 81% |
| MMLU-Pro | — | 74% |
| HLE | — | 10% |
| FrontierScience | — | 74% |
| SimpleQA | — | 81% |
| Instruction FollowingQwen2.5-1M wins | ||
| IFEval | 69.6% | 84% |
| Multilingual | ||
| MGSM | — | 81% |
| MMLU-ProX | — | 80% |
| MathematicsQwen2.5-1M wins | ||
| MATH-500 | 65.8% | 83% |
| AIME 2023 | — | 85% |
| AIME 2024 | — | 87% |
| AIME 2025 | — | 86% |
| HMMT Feb 2023 | — | 81% |
| HMMT Feb 2024 | — | 83% |
| HMMT Feb 2025 | — | 82% |
| BRUMO 2025 | — | 84% |
Qwen2.5-1M is ahead overall, 62 to 44. The biggest single separator in this matchup is GPQA, where the scores are 28.7% and 83%.
Qwen2.5-1M has the edge for knowledge tasks in this comparison, averaging 62.1 versus 28.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for math in this comparison, averaging 84.6 versus 65.8. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for reasoning in this comparison, averaging 80.9 versus 41.4. Inside this category, MuSR is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for instruction following in this comparison, averaging 84 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.