Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Kimi K2
53
1/8 categoriesQwen3.5-27B
71
Winner · 3/8 categoriesKimi K2· Qwen3.5-27B
Pick Qwen3.5-27B if you want the stronger benchmark profile. Kimi K2 only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3.5-27B is clearly ahead on the aggregate, 71 to 53. 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 58.2. The single biggest benchmark swing on the page is LiveCodeBench, 53.7% to 80.7%. Kimi K2 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Qwen3.5-27B is the reasoning model in the pair, while Kimi K2 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.5-27B gives you the larger context window at 262K, compared with 128K for Kimi K2.
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 | Kimi K2 | Qwen3.5-27B |
|---|---|---|
| AgenticKimi K2 wins | ||
| Terminal-Bench 2.0 | 47.1% | 41.6% |
| BrowseComp | 60.2% | 61% |
| tau2-bench | 66.1% | 79% |
| OSWorld-Verified | — | 56.2% |
| CodingQwen3.5-27B wins | ||
| SWE-bench Verified | 65.8% | 72.4% |
| LiveCodeBench | 53.7% | 80.7% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 75% |
| Reasoning | ||
| hle | 44.9% | — |
| LongBench v2 | — | 60.6% |
| KnowledgeQwen3.5-27B wins | ||
| MMLU | 89.5% | — |
| GPQA | 75.1% | 85.5% |
| SuperGPQA | 57.2% | 65.6% |
| MMLU-Pro | 81.1% | 86.1% |
| SimpleQA | 31% | — |
| Instruction FollowingQwen3.5-27B wins | ||
| IFEval | 89.8% | 95% |
| Multilingual | ||
| sweMultilingual | 61.1% | — |
| MMLU-ProX | — | 82.2% |
| Mathematics | ||
| AIME 2024 | 69.6% | — |
| AIME 2025 | 49.5% | — |
| MATH-500 | 97.4% | — |
| HMMT Feb 2025 | 38.8% | — |
Qwen3.5-27B is ahead overall, 71 to 53. The biggest single separator in this matchup is LiveCodeBench, where the scores are 53.7% and 80.7%.
Qwen3.5-27B has the edge for knowledge tasks in this comparison, averaging 80.6 versus 64. Inside this category, GPQA 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 58.2. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Kimi K2 has the edge for agentic tasks in this comparison, averaging 52.1 versus 51.6. Inside this category, tau2-bench 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 89.8. 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.