Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
o4-mini (high)
58
1/8 categoriesQwen3.5-27B
71
Winner · 6/8 categorieso4-mini (high)· Qwen3.5-27B
Pick Qwen3.5-27B if you want the stronger benchmark profile. o4-mini (high) only becomes the better choice if agentic is the priority.
Qwen3.5-27B is clearly ahead on the aggregate, 71 to 58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5-27B's sharpest advantage is in coding, where it averages 77.6 against 44.9. The single biggest benchmark swing on the page is LiveCodeBench, 34% to 80.7%. o4-mini (high) does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Qwen3.5-27B gives you the larger context window at 262K, compared with 200K for o4-mini (high).
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 | o4-mini (high) | Qwen3.5-27B |
|---|---|---|
| Agentico4-mini (high) wins | ||
| Terminal-Bench 2.0 | 58% | 41.6% |
| BrowseComp | 64% | 61% |
| OSWorld-Verified | 55% | 56.2% |
| tau2-bench | — | 79% |
| CodingQwen3.5-27B wins | ||
| HumanEval | 74% | — |
| SWE-bench Verified | 68.1% | 72.4% |
| LiveCodeBench | 34% | 80.7% |
| SWE-bench Pro | 42% | — |
| Multimodal & GroundedQwen3.5-27B wins | ||
| MMMU-Pro | 66% | 75% |
| OfficeQA Pro | 71% | — |
| ReasoningQwen3.5-27B wins | ||
| MuSR | 78% | — |
| BBH | 83% | — |
| LongBench v2 | 75% | 60.6% |
| MRCRv2 | 74% | — |
| ARC-AGI-2 | 2.4% | — |
| KnowledgeQwen3.5-27B wins | ||
| MMLU | 82% | — |
| GPQA | 82% | 85.5% |
| SuperGPQA | 80% | 65.6% |
| MMLU-Pro | 76% | 86.1% |
| HLE | 13% | — |
| FrontierScience | 73% | — |
| SimpleQA | 80% | — |
| Instruction FollowingQwen3.5-27B wins | ||
| IFEval | 83% | 95% |
| MultilingualQwen3.5-27B wins | ||
| MGSM | 83% | — |
| MMLU-ProX | 81% | 82.2% |
| Mathematics | ||
| AIME 2023 | 83% | — |
| AIME 2024 | 93.4% | — |
| AIME 2025 | 92.7% | — |
| HMMT Feb 2023 | 79% | — |
| HMMT Feb 2024 | 81% | — |
| HMMT Feb 2025 | 80% | — |
| BRUMO 2025 | 82% | — |
| MATH-500 | 84% | — |
Qwen3.5-27B is ahead overall, 71 to 58. The biggest single separator in this matchup is LiveCodeBench, where the scores are 34% and 80.7%.
Qwen3.5-27B has the edge for knowledge tasks in this comparison, averaging 80.6 versus 62.7. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for coding in this comparison, averaging 77.6 versus 44.9. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for reasoning in this comparison, averaging 60.6 versus 57.2. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
o4-mini (high) has the edge for agentic tasks in this comparison, averaging 58.5 versus 51.6. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for multimodal and grounded tasks in this comparison, averaging 75 versus 68.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for instruction following in this comparison, averaging 95 versus 83. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Qwen3.5-27B has the edge for multilingual tasks in this comparison, averaging 82.2 versus 81.7. Inside this category, MMLU-ProX 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.